Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3743 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.5246. Min Act: -0.1700
Data Index: 3867713 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.5246. Min Act: -0.1700
Data Index: 6809874 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.5246. Min Act: -0.1700
Data Index: 5659450 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.4308. Min Act: -0.1700
Data Index: 8568463 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.2121. Min Act: -0.1700
Data Index: 6720830 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.1808. Min Act: -0.1700
Data Index: 469972 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.1808. Min Act: -0.1700
Data Index: 2862110 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.1496. Min Act: -0.1700
Data Index: 418292 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.1496. Min Act: -0.1700
Data Index: 4426815 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.0871. Min Act: -0.1700
Data Index: 1871956 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.0558. Min Act: -0.1700
Data Index: 3137639 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.0246. Min Act: -0.1700
Data Index: 5122454 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9933. Min Act: -0.1700
Data Index: 1458864 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5246. Min Range: -6.5246
Max Act: 6.0246. Min Act: -0.1700
Data Index: 6058176 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9933. Min Act: -0.1700
Data Index: 5762588 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9933. Min Act: -0.1700
Data Index: 3382305 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9933. Min Act: -0.1700
Data Index: 5721996 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9933. Min Act: -0.1700
Data Index: 1229380 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9933. Min Act: -0.1700
Data Index: 7768117 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5246. Min Range: -6.5246
Max Act: 5.9308. Min Act: -0.1700
Data Index: 2955990 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19