Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2405 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.5711. Min Act: -0.1700
Data Index: 4465984 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.4741. Min Act: -0.1700
Data Index: 8217801 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.4578. Min Act: -0.1700
Data Index: 7180864 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.4578. Min Act: -0.1700
Data Index: 2414887 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.4253. Min Act: -0.1700
Data Index: 532145 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.4090. Min Act: -0.1700
Data Index: 4597456 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.4090. Min Act: -0.1700
Data Index: 7930804 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.4090. Min Act: -0.1700
Data Index: 4292169 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.4090. Min Act: -0.1700
Data Index: 5533426 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3927. Min Act: -0.1700
Data Index: 4665620 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3763. Min Act: -0.1700
Data Index: 1100515 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3763. Min Act: -0.1700
Data Index: 2657883 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3763. Min Act: -0.1700
Data Index: 2258216 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3600. Min Act: -0.1700
Data Index: 4857931 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3600. Min Act: -0.1700
Data Index: 6917629 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3600. Min Act: -0.1700
Data Index: 1485335 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3600. Min Act: -0.1700
Data Index: 405905 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3600. Min Act: -0.1700
Data Index: 6192397 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3600. Min Act: -0.1700
Data Index: 3044765 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5711. Min Range: -2.5711
Max Act: 2.3600. Min Act: -0.1700
Data Index: 4524691 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19