Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4255 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.9116. Min Act: -0.1700
Data Index: 8732369 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.8179. Min Act: -0.1700
Data Index: 8343534 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.7241. Min Act: -0.1700
Data Index: 241512 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.7241. Min Act: -0.1700
Data Index: 274143 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.6304. Min Act: -0.1700
Data Index: 8732370 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.5991. Min Act: -0.1700
Data Index: 426868 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.5991. Min Act: -0.1700
Data Index: 5987226 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.5366. Min Act: -0.1700
Data Index: 3067941 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.5366. Min Act: -0.1700
Data Index: 6281454 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.5366. Min Act: -0.1700
Data Index: 2047877 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.5054. Min Act: -0.1700
Data Index: 7367029 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.5054. Min Act: -0.1700
Data Index: 3845602 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.5054. Min Act: -0.1700
Data Index: 8163469 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.4741. Min Act: -0.1700
Data Index: 7252888 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.4429. Min Act: -0.1700
Data Index: 7455938 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.4741. Min Act: -0.1700
Data Index: 1117903 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.4741. Min Act: -0.1700
Data Index: 6462351 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.5054. Min Act: -0.1700
Data Index: 1777719 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.4741. Min Act: -0.1700
Data Index: 1354540 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9116. Min Range: -5.9116
Max Act: 5.4429. Min Act: -0.1700
Data Index: 4911244 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19