Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3294 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.9554. Min Act: -0.1700
Data Index: 4884768 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.9554. Min Act: -0.1700
Data Index: 6176060 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.9242. Min Act: -0.1700
Data Index: 8311843 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.8304. Min Act: -0.1700
Data Index: 4883570 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.8304. Min Act: -0.1700
Data Index: 159536 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7679. Min Act: -0.1700
Data Index: 7326615 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.7992. Min Act: -0.1700
Data Index: 8668653 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6742. Min Act: -0.1700
Data Index: 1238765 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6742. Min Act: -0.1700
Data Index: 5785225 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6429. Min Act: -0.1700
Data Index: 3339628 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6117. Min Act: -0.1700
Data Index: 5489708 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6429. Min Act: -0.1700
Data Index: 3036482 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5492. Min Act: -0.1700
Data Index: 6686705 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5804. Min Act: -0.1700
Data Index: 4160885 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.6117. Min Act: -0.1700
Data Index: 6951995 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5492. Min Act: -0.1700
Data Index: 2999526 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5804. Min Act: -0.1700
Data Index: 7716956 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5492. Min Act: -0.1700
Data Index: 1692860 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5492. Min Act: -0.1700
Data Index: 5829155 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9554. Min Range: -5.9554
Max Act: 5.5179. Min Act: -0.1700
Data Index: 2341722 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #19