Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2216 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.6420. Min Act: -0.1700
Data Index: 3034612 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.5483. Min Act: -0.1700
Data Index: 6477528 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4858. Min Act: -0.1700
Data Index: 3904742 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4858. Min Act: -0.1700
Data Index: 7764084 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.5170. Min Act: -0.1700
Data Index: 8225616 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4858. Min Act: -0.1700
Data Index: 4910444 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4545. Min Act: -0.1700
Data Index: 230861 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4545. Min Act: -0.1700
Data Index: 3070677 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4545. Min Act: -0.1700
Data Index: 6449808 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4545. Min Act: -0.1700
Data Index: 3623559 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4233. Min Act: -0.1700
Data Index: 3798988 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4233. Min Act: -0.1700
Data Index: 3891029 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4233. Min Act: -0.1700
Data Index: 2966243 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4545. Min Act: -0.1700
Data Index: 6775486 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.4233. Min Act: -0.1700
Data Index: 8734796 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.3608. Min Act: -0.1700
Data Index: 6369928 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.3920. Min Act: -0.1700
Data Index: 8296318 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.3608. Min Act: -0.1700
Data Index: 1093409 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.3608. Min Act: -0.1700
Data Index: 6038975 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6420. Min Range: -4.6420
Max Act: 4.3608. Min Act: -0.1700
Data Index: 1067517 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #19