Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4259 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.8964. Min Act: -0.1700
Data Index: 2685386 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.8339. Min Act: -0.1700
Data Index: 700257 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.7714. Min Act: -0.1700
Data Index: 2570904 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.7401. Min Act: -0.1700
Data Index: 1915849 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.6776. Min Act: -0.1700
Data Index: 7291012 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.7089. Min Act: -0.1700
Data Index: 6552674 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.7089. Min Act: -0.1700
Data Index: 2867968 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.7089. Min Act: -0.1700
Data Index: 926789 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.6776. Min Act: -0.1700
Data Index: 2081237 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.6464. Min Act: -0.1700
Data Index: 7266512 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.6776. Min Act: -0.1700
Data Index: 1275450 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.6464. Min Act: -0.1700
Data Index: 7123272 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.6464. Min Act: -0.1700
Data Index: 8495760 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.6151. Min Act: -0.1700
Data Index: 20080 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.6151. Min Act: -0.1700
Data Index: 3097659 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.6151. Min Act: -0.1700
Data Index: 5526919 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.5839. Min Act: -0.1700
Data Index: 3115463 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.5526. Min Act: -0.1700
Data Index: 2257847 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.5839. Min Act: -0.1700
Data Index: 8623625 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.5214. Min Act: -0.1700
Data Index: 7482242 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19