Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5230 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4022. Min Range: -6.4022
Max Act: 6.4022. Min Act: -0.1700
Data Index: 5220661 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4022. Min Range: -6.4022
Max Act: 6.2147. Min Act: -0.1700
Data Index: 2975335 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4022. Min Range: -6.4022
Max Act: 6.0272. Min Act: -0.1700
Data Index: 3211920 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.9647. Min Act: -0.1700
Data Index: 5752448 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.9335. Min Act: -0.1700
Data Index: 8182559 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.9022. Min Act: -0.1700
Data Index: 4780281 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.8710. Min Act: -0.1700
Data Index: 604220 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.9022. Min Act: -0.1700
Data Index: 6088107 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.8710. Min Act: -0.1700
Data Index: 5002900 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.7772. Min Act: -0.1700
Data Index: 247898 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.7772. Min Act: -0.1700
Data Index: 466098 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.8085. Min Act: -0.1700
Data Index: 1826148 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.8085. Min Act: -0.1700
Data Index: 1535796 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.8085. Min Act: -0.1700
Data Index: 7045152 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.8085. Min Act: -0.1700
Data Index: 264034 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.7772. Min Act: -0.1700
Data Index: 2476507 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.7772. Min Act: -0.1700
Data Index: 112834 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.7772. Min Act: -0.1700
Data Index: 2331460 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.7460. Min Act: -0.1700
Data Index: 6202799 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4022. Min Range: -6.4022
Max Act: 5.7460. Min Act: -0.1700
Data Index: 6958990 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19