Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4107 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2653. Min Range: -7.2653
Max Act: 7.2653. Min Act: -0.1700
Data Index: 5232852 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.9528. Min Act: -0.1700
Data Index: 903700 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.9840. Min Act: -0.1700
Data Index: 6540983 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.8278. Min Act: -0.1700
Data Index: 648926 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.7965. Min Act: -0.1700
Data Index: 7888344 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.7653. Min Act: -0.1700
Data Index: 2822693 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.7965. Min Act: -0.1700
Data Index: 1920544 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.7340. Min Act: -0.1700
Data Index: 4975713 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.7340. Min Act: -0.1700
Data Index: 531488 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6715. Min Act: -0.1700
Data Index: 3046613 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6715. Min Act: -0.1700
Data Index: 4999114 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6715. Min Act: -0.1700
Data Index: 4835309 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6715. Min Act: -0.1700
Data Index: 3074303 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6715. Min Act: -0.1700
Data Index: 2882220 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6403. Min Act: -0.1700
Data Index: 3509473 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6715. Min Act: -0.1700
Data Index: 7363238 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6403. Min Act: -0.1700
Data Index: 5217438 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6715. Min Act: -0.1700
Data Index: 1999823 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6715. Min Act: -0.1700
Data Index: 3077177 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2653. Min Range: -7.2653
Max Act: 6.6715. Min Act: -0.1700
Data Index: 6698747 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19