Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 974 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2166. Min Range: -6.2166
Max Act: 6.2166. Min Act: -0.1700
Data Index: 7883580 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2166. Min Range: -6.2166
Max Act: 6.1228. Min Act: -0.1700
Data Index: 561589 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2166. Min Range: -6.2166
Max Act: 6.0916. Min Act: -0.1700
Data Index: 5177473 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2166. Min Range: -6.2166
Max Act: 6.0603. Min Act: -0.1700
Data Index: 2629304 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.9666. Min Act: -0.1700
Data Index: 1461780 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.9666. Min Act: -0.1700
Data Index: 6096319 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.8728. Min Act: -0.1700
Data Index: 8013743 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.8728. Min Act: -0.1700
Data Index: 5984266 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.8728. Min Act: -0.1700
Data Index: 7778547 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.8416. Min Act: -0.1700
Data Index: 8802527 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.8416. Min Act: -0.1700
Data Index: 3070571 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.8416. Min Act: -0.1700
Data Index: 590437 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.8103. Min Act: -0.1700
Data Index: 1491691 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.8103. Min Act: -0.1700
Data Index: 2512466 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.7791. Min Act: -0.1700
Data Index: 5914550 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.7791. Min Act: -0.1700
Data Index: 7687729 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.7791. Min Act: -0.1700
Data Index: 4132968 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.7791. Min Act: -0.1700
Data Index: 5456732 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.7478. Min Act: -0.1700
Data Index: 6150393 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2166. Min Range: -6.2166
Max Act: 5.7166. Min Act: -0.1700
Data Index: 904465 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19