Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4622 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2628. Min Range: -7.2628
Max Act: 7.2628. Min Act: -0.1700
Data Index: 7183453 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2628. Min Range: -7.2628
Max Act: 7.0753. Min Act: -0.1700
Data Index: 2434397 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2628. Min Range: -7.2628
Max Act: 7.0128. Min Act: -0.1700
Data Index: 2447154 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.9503. Min Act: -0.1700
Data Index: 7816763 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.8878. Min Act: -0.1700
Data Index: 551449 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.8565. Min Act: -0.1700
Data Index: 6097396 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.8878. Min Act: -0.1700
Data Index: 6356084 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.8878. Min Act: -0.1700
Data Index: 977939 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.8253. Min Act: -0.1700
Data Index: 6227532 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.8253. Min Act: -0.1700
Data Index: 7738725 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.7940. Min Act: -0.1700
Data Index: 3287346 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.7315. Min Act: -0.1700
Data Index: 3411467 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.7628. Min Act: -0.1700
Data Index: 8739136 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.7315. Min Act: -0.1700
Data Index: 3424676 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.6378. Min Act: -0.1700
Data Index: 4468450 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.6690. Min Act: -0.1700
Data Index: 4481049 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.6690. Min Act: -0.1700
Data Index: 6384355 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.6690. Min Act: -0.1700
Data Index: 888553 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.6378. Min Act: -0.1700
Data Index: 286889 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2628. Min Range: -7.2628
Max Act: 6.6378. Min Act: -0.1700
Data Index: 5605401 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19