Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 269 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2650. Min Range: -7.2650
Max Act: 7.2650. Min Act: -0.1700
Data Index: 7018360 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.8900. Min Act: -0.1700
Data Index: 2071426 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.8900. Min Act: -0.1700
Data Index: 6644003 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.8275. Min Act: -0.1700
Data Index: 3966013 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.8275. Min Act: -0.1700
Data Index: 7683518 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7650. Min Act: -0.1700
Data Index: 1632197 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7337. Min Act: -0.1700
Data Index: 2136223 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7337. Min Act: -0.1700
Data Index: 657753 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7025. Min Act: -0.1700
Data Index: 7394409 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7025. Min Act: -0.1700
Data Index: 3988825 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.7025. Min Act: -0.1700
Data Index: 8778853 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.6712. Min Act: -0.1700
Data Index: 8006189 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.6087. Min Act: -0.1700
Data Index: 2701735 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.6087. Min Act: -0.1700
Data Index: 7057743 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.6087. Min Act: -0.1700
Data Index: 1591104 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.5775. Min Act: -0.1700
Data Index: 3049 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.5775. Min Act: -0.1700
Data Index: 5400954 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.5775. Min Act: -0.1700
Data Index: 7715291 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.5462. Min Act: -0.1700
Data Index: 1591105 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2650. Min Range: -7.2650
Max Act: 6.5150. Min Act: -0.1700
Data Index: 4373607 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19