Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3296 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.9397. Min Act: -0.1700
Data Index: 112311 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.9085. Min Act: -0.1700
Data Index: 8218441 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.8147. Min Act: -0.1700
Data Index: 8182354 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.7835. Min Act: -0.1700
Data Index: 5699439 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.7522. Min Act: -0.1700
Data Index: 1779456 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.7522. Min Act: -0.1700
Data Index: 7882842 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.7210. Min Act: -0.1700
Data Index: 5661522 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.7210. Min Act: -0.1700
Data Index: 8756034 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.6897. Min Act: -0.1700
Data Index: 5686677 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.6585. Min Act: -0.1700
Data Index: 4974505 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.6585. Min Act: -0.1700
Data Index: 1058806 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.6585. Min Act: -0.1700
Data Index: 7485507 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.6272. Min Act: -0.1700
Data Index: 1795805 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.5960. Min Act: -0.1700
Data Index: 4169818 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.5960. Min Act: -0.1700
Data Index: 3419614 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.5960. Min Act: -0.1700
Data Index: 5956680 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.5960. Min Act: -0.1700
Data Index: 3557150 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.5647. Min Act: -0.1700
Data Index: 1336825 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.5335. Min Act: -0.1700
Data Index: 5390809 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9397. Min Range: -5.9397
Max Act: 5.5335. Min Act: -0.1700
Data Index: 5141803 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19