Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 382 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.9065. Min Act: -0.1700
Data Index: 3192864 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.5940. Min Act: -0.1700
Data Index: 6349594 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.5315. Min Act: -0.1700
Data Index: 1888458 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.5315. Min Act: -0.1700
Data Index: 5993767 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.5003. Min Act: -0.1700
Data Index: 7571811 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.5003. Min Act: -0.1700
Data Index: 2203328 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4378. Min Act: -0.1700
Data Index: 7982604 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4378. Min Act: -0.1700
Data Index: 4567598 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.5003. Min Act: -0.1700
Data Index: 2983024 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4378. Min Act: -0.1700
Data Index: 8546721 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4378. Min Act: -0.1700
Data Index: 8389416 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4378. Min Act: -0.1700
Data Index: 8020355 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4378. Min Act: -0.1700
Data Index: 1684299 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4378. Min Act: -0.1700
Data Index: 7819254 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4690. Min Act: -0.1700
Data Index: 4099557 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4065. Min Act: -0.1700
Data Index: 614518 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.4065. Min Act: -0.1700
Data Index: 8000937 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.3440. Min Act: -0.1700
Data Index: 1304463 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.3753. Min Act: -0.1700
Data Index: 5833917 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9065. Min Range: -5.9065
Max Act: 5.3128. Min Act: -0.1700
Data Index: 6579585 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19