Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3395 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.5290. Min Act: -0.1700
Data Index: 423234 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.4665. Min Act: -0.1700
Data Index: 3949167 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.4353. Min Act: -0.1700
Data Index: 3345630 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.3728. Min Act: -0.1700
Data Index: 4499610 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.3415. Min Act: -0.1700
Data Index: 7340128 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.3415. Min Act: -0.1700
Data Index: 3215220 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.2790. Min Act: -0.1700
Data Index: 4813840 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.2790. Min Act: -0.1700
Data Index: 109076 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.2165. Min Act: -0.1700
Data Index: 5932454 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.2478. Min Act: -0.1700
Data Index: 637432 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.2165. Min Act: -0.1700
Data Index: 2867621 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.2478. Min Act: -0.1700
Data Index: 8310225 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.2478. Min Act: -0.1700
Data Index: 663209 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.2165. Min Act: -0.1700
Data Index: 1781753 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.1853. Min Act: -0.1700
Data Index: 7492767 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.1853. Min Act: -0.1700
Data Index: 558502 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.1540. Min Act: -0.1700
Data Index: 6842266 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.1540. Min Act: -0.1700
Data Index: 501529 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.1540. Min Act: -0.1700
Data Index: 6296995 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5290. Min Range: -6.5290
Max Act: 6.1228. Min Act: -0.1700
Data Index: 5583363 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #19