Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 638 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.5236. Min Act: -0.1700
Data Index: 1503149 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.4924. Min Act: -0.1700
Data Index: 4200911 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.4299. Min Act: -0.1700
Data Index: 604985 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.4299. Min Act: -0.1700
Data Index: 3075550 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3674. Min Act: -0.1700
Data Index: 3380489 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3674. Min Act: -0.1700
Data Index: 1252930 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3674. Min Act: -0.1700
Data Index: 4114214 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3361. Min Act: -0.1700
Data Index: 8157902 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3674. Min Act: -0.1700
Data Index: 436396 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3049. Min Act: -0.1700
Data Index: 1224324 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3361. Min Act: -0.1700
Data Index: 7346026 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3049. Min Act: -0.1700
Data Index: 5379528 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3049. Min Act: -0.1700
Data Index: 435549 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3049. Min Act: -0.1700
Data Index: 7099185 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.2736. Min Act: -0.1700
Data Index: 6776006 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3049. Min Act: -0.1700
Data Index: 2982866 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.2736. Min Act: -0.1700
Data Index: 3698328 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3049. Min Act: -0.1700
Data Index: 3575314 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3049. Min Act: -0.1700
Data Index: 5437549 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5236. Min Range: -5.5236
Max Act: 5.3049. Min Act: -0.1700
Data Index: 2804328 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19