Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4090 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.4077. Min Act: -0.1700
Data Index: 2710822 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.2827. Min Act: -0.1700
Data Index: 4245434 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.2515. Min Act: -0.1700
Data Index: 6383049 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.2827. Min Act: -0.1700
Data Index: 6502283 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.2202. Min Act: -0.1700
Data Index: 2438388 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.2202. Min Act: -0.1700
Data Index: 6763006 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.2515. Min Act: -0.1700
Data Index: 8252633 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.1265. Min Act: -0.1700
Data Index: 6482148 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.1265. Min Act: -0.1700
Data Index: 7688541 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0952. Min Act: -0.1700
Data Index: 1949095 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0952. Min Act: -0.1700
Data Index: 4718652 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0952. Min Act: -0.1700
Data Index: 2236587 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0952. Min Act: -0.1700
Data Index: 2060640 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0640. Min Act: -0.1700
Data Index: 4485401 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0640. Min Act: -0.1700
Data Index: 3060256 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0327. Min Act: -0.1700
Data Index: 387452 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0640. Min Act: -0.1700
Data Index: 3255995 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0327. Min Act: -0.1700
Data Index: 7919844 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0327. Min Act: -0.1700
Data Index: 3694016 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4077. Min Range: -6.4077
Max Act: 6.0327. Min Act: -0.1700
Data Index: 5513140 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19