Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5217 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.3112. Min Range: -17.3112
Max Act: 17.3112. Min Act: -0.1700
Data Index: 6032609 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.3112. Min Range: -17.3112
Max Act: 17.0612. Min Act: -0.1700
Data Index: 1711600 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.9362. Min Act: -0.1700
Data Index: 1567310 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.9362. Min Act: -0.1700
Data Index: 7714935 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.8112. Min Act: -0.1700
Data Index: 1610946 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.6862. Min Act: -0.1700
Data Index: 1157236 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.6862. Min Act: -0.1700
Data Index: 6281712 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.6862. Min Act: -0.1700
Data Index: 2872660 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.6862. Min Act: -0.1700
Data Index: 6957781 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.5612. Min Act: -0.1700
Data Index: 8768599 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.5612. Min Act: -0.1700
Data Index: 4862925 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.5612. Min Act: -0.1700
Data Index: 6659411 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.5612. Min Act: -0.1700
Data Index: 7356431 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.4362. Min Act: -0.1700
Data Index: 6216011 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.4362. Min Act: -0.1700
Data Index: 7930675 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.4362. Min Act: -0.1700
Data Index: 6908621 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.4362. Min Act: -0.1700
Data Index: 3985124 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.4362. Min Act: -0.1700
Data Index: 4100526 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.3112. Min Act: -0.1700
Data Index: 5097643 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.3112. Min Range: -17.3112
Max Act: 16.3112. Min Act: -0.1700
Data Index: 7217808 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19