Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2624 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.5376. Min Act: -0.1700
Data Index: 5882740 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.4126. Min Act: -0.1700
Data Index: 2606120 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.2876. Min Act: -0.1700
Data Index: 5013291 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.2251. Min Act: -0.1700
Data Index: 2673560 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.1939. Min Act: -0.1700
Data Index: 5084235 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.1314. Min Act: -0.1700
Data Index: 4141141 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.1314. Min Act: -0.1700
Data Index: 3463468 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.1001. Min Act: -0.1700
Data Index: 2091021 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.1001. Min Act: -0.1700
Data Index: 3650205 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0689. Min Act: -0.1700
Data Index: 1503473 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0689. Min Act: -0.1700
Data Index: 2971026 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0376. Min Act: -0.1700
Data Index: 1048207 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0376. Min Act: -0.1700
Data Index: 8767492 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0376. Min Act: -0.1700
Data Index: 6991804 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0376. Min Act: -0.1700
Data Index: 8139047 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0376. Min Act: -0.1700
Data Index: 666193 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0376. Min Act: -0.1700
Data Index: 2767282 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0376. Min Act: -0.1700
Data Index: 6625325 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0064. Min Act: -0.1700
Data Index: 6265366 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5376. Min Range: -5.5376
Max Act: 5.0064. Min Act: -0.1699
Data Index: 3392805 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19