Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3433 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3503. Min Range: -7.3503
Max Act: 7.3503. Min Act: -0.1700
Data Index: 3619230 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3503. Min Range: -7.3503
Max Act: 7.1940. Min Act: -0.1700
Data Index: 3316464 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3503. Min Range: -7.3503
Max Act: 7.1003. Min Act: -0.1700
Data Index: 3335412 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3503. Min Range: -7.3503
Max Act: 7.1003. Min Act: -0.1700
Data Index: 5584451 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3503. Min Range: -7.3503
Max Act: 7.0065. Min Act: -0.1700
Data Index: 5946930 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.9753. Min Act: -0.1700
Data Index: 7355776 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3503. Min Range: -7.3503
Max Act: 7.0065. Min Act: -0.1700
Data Index: 1000407 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.9753. Min Act: -0.1700
Data Index: 4979212 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.9128. Min Act: -0.1700
Data Index: 3670266 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.8815. Min Act: -0.1700
Data Index: 3991701 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.8815. Min Act: -0.1700
Data Index: 7355777 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.8503. Min Act: -0.1700
Data Index: 1592973 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.8190. Min Act: -0.1700
Data Index: 5664412 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.8503. Min Act: -0.1700
Data Index: 5559279 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.7878. Min Act: -0.1700
Data Index: 5886000 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.7565. Min Act: -0.1700
Data Index: 6999259 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.7253. Min Act: -0.1700
Data Index: 286002 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.7565. Min Act: -0.1700
Data Index: 6122521 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.7253. Min Act: -0.1700
Data Index: 7694932 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3503. Min Range: -7.3503
Max Act: 6.6628. Min Act: -0.1700
Data Index: 4889206 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19