Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 64 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.9545. Min Act: -0.1700
Data Index: 5321632 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.8295. Min Act: -0.1700
Data Index: 1335922 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.7670. Min Act: -0.1700
Data Index: 2962152 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.7045. Min Act: -0.1700
Data Index: 4047387 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.6420. Min Act: -0.1700
Data Index: 8050440 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.5795. Min Act: -0.1700
Data Index: 3315321 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.5170. Min Act: -0.1700
Data Index: 3893066 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.5170. Min Act: -0.1700
Data Index: 2007964 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.3920. Min Act: -0.1700
Data Index: 1281955 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.3920. Min Act: -0.1700
Data Index: 6807483 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.3920. Min Act: -0.1700
Data Index: 779781 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.3295. Min Act: -0.1700
Data Index: 1871286 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.2670. Min Act: -0.1700
Data Index: 7431143 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.2670. Min Act: -0.1700
Data Index: 7722988 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.2670. Min Act: -0.1700
Data Index: 8359100 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.2670. Min Act: -0.1700
Data Index: 1002831 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.2045. Min Act: -0.1700
Data Index: 4015443 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.2045. Min Act: -0.1700
Data Index: 1851962 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.2045. Min Act: -0.1700
Data Index: 5618617 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9545. Min Range: -8.9545
Max Act: 8.2045. Min Act: -0.1700
Data Index: 4572235 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19