Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4447 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.8352. Min Act: -0.1700
Data Index: 8652369 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.7875. Min Act: -0.1700
Data Index: 7065143 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.7077. Min Act: -0.1700
Data Index: 2683395 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.6917. Min Act: -0.1700
Data Index: 8514432 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.6596. Min Act: -0.1700
Data Index: 5740048 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.6596. Min Act: -0.1700
Data Index: 7219695 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.6436. Min Act: -0.1700
Data Index: 8389121 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.6436. Min Act: -0.1700
Data Index: 7527599 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5792. Min Act: -0.1700
Data Index: 4736641 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5792. Min Act: -0.1700
Data Index: 4027879 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5792. Min Act: -0.1700
Data Index: 4037431 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5792. Min Act: -0.1700
Data Index: 3925681 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5792. Min Act: -0.1700
Data Index: 7338659 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5631. Min Act: -0.1700
Data Index: 1616371 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5470. Min Act: -0.1700
Data Index: 116338 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5631. Min Act: -0.1700
Data Index: 3038351 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5631. Min Act: -0.1700
Data Index: 505832 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5631. Min Act: -0.1700
Data Index: 5740047 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5631. Min Act: -0.1700
Data Index: 6128515 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8352. Min Range: -2.8352
Max Act: 2.5631. Min Act: -0.1700
Data Index: 8514431 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19