Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4116 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0925. Min Range: -5.0925
Max Act: 5.0925. Min Act: -0.1700
Data Index: 3552296 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0925. Min Range: -5.0925
Max Act: 5.0925. Min Act: -0.1700
Data Index: 651340 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.9988. Min Act: -0.1700
Data Index: 8698443 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.9675. Min Act: -0.1700
Data Index: 5275836 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.9675. Min Act: -0.1700
Data Index: 8266790 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.9675. Min Act: -0.1700
Data Index: 1198203 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.9363. Min Act: -0.1700
Data Index: 7738369 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.9050. Min Act: -0.1700
Data Index: 7903500 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.9050. Min Act: -0.1700
Data Index: 5279071 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.8425. Min Act: -0.1700
Data Index: 5477192 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.8425. Min Act: -0.1700
Data Index: 5996342 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.8113. Min Act: -0.1700
Data Index: 6327289 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.8113. Min Act: -0.1700
Data Index: 189681 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.8113. Min Act: -0.1700
Data Index: 7758762 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.7800. Min Act: -0.1700
Data Index: 6545129 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.7488. Min Act: -0.1700
Data Index: 4612840 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.7488. Min Act: -0.1700
Data Index: 2236612 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.7175. Min Act: -0.1700
Data Index: 3945928 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.7175. Min Act: -0.1700
Data Index: 5651392 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0925. Min Range: -5.0925
Max Act: 4.7488. Min Act: -0.1700
Data Index: 7665789 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19