Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2307. Min Range: -4.2307
Max Act: 4.2307. Min Act: -0.1700
Data Index: 3724146 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2307. Min Range: -4.2307
Max Act: 4.1370. Min Act: -0.1700
Data Index: 7337263 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2307. Min Range: -4.2307
Max Act: 4.0745. Min Act: -0.1700
Data Index: 1359989 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2307. Min Range: -4.2307
Max Act: 4.0120. Min Act: -0.1700
Data Index: 1810928 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2307. Min Range: -4.2307
Max Act: 4.0120. Min Act: -0.1700
Data Index: 7953690 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2307. Min Range: -4.2307
Max Act: 4.0120. Min Act: -0.1700
Data Index: 4485702 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2307. Min Range: -4.2307
Max Act: 4.0120. Min Act: -0.1700
Data Index: 7458287 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9807. Min Act: -0.1700
Data Index: 5098026 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9807. Min Act: -0.1700
Data Index: 371056 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9807. Min Act: -0.1700
Data Index: 2005845 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9494. Min Act: -0.1700
Data Index: 4878685 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9807. Min Act: -0.1700
Data Index: 8001331 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9807. Min Act: -0.1700
Data Index: 5776123 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9182. Min Act: -0.1700
Data Index: 8372245 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9494. Min Act: -0.1700
Data Index: 8258299 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9182. Min Act: -0.1700
Data Index: 5027408 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9182. Min Act: -0.1700
Data Index: 1464058 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9182. Min Act: -0.1700
Data Index: 5967489 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.9182. Min Act: -0.1700
Data Index: 8229483 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2307. Min Range: -4.2307
Max Act: 3.8869. Min Act: -0.1700
Data Index: 4635011 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19