Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2676 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0295. Min Range: -7.0295
Max Act: 7.0295. Min Act: -0.1700
Data Index: 6543561 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0295. Min Range: -7.0295
Max Act: 7.0295. Min Act: -0.1700
Data Index: 1953490 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.9983. Min Act: -0.1700
Data Index: 984388 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.9670. Min Act: -0.1700
Data Index: 2384212 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.9358. Min Act: -0.1700
Data Index: 4831019 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.8733. Min Act: -0.1700
Data Index: 890921 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.8420. Min Act: -0.1700
Data Index: 4231534 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.8108. Min Act: -0.1700
Data Index: 2450611 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.8108. Min Act: -0.1700
Data Index: 7528097 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.7795. Min Act: -0.1700
Data Index: 4432208 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.7795. Min Act: -0.1700
Data Index: 651098 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.7483. Min Act: -0.1700
Data Index: 1732193 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.7483. Min Act: -0.1700
Data Index: 3905609 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.6858. Min Act: -0.1700
Data Index: 1761957 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.6545. Min Act: -0.1700
Data Index: 6155368 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.6233. Min Act: -0.1700
Data Index: 6243007 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.5295. Min Act: -0.1700
Data Index: 3968320 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.4983. Min Act: -0.1700
Data Index: 5129082 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.4983. Min Act: -0.1700
Data Index: 1463668 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0295. Min Range: -7.0295
Max Act: 6.5295. Min Act: -0.1700
Data Index: 2342312 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19