Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5017 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.5597. Min Act: -0.1700
Data Index: 1373525 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.4347. Min Act: -0.1700
Data Index: 5305321 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.3410. Min Act: -0.1700
Data Index: 3983459 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.2785. Min Act: -0.1700
Data Index: 7315530 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.2785. Min Act: -0.1700
Data Index: 5056596 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.2472. Min Act: -0.1700
Data Index: 7741885 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.2160. Min Act: -0.1700
Data Index: 2350392 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.2160. Min Act: -0.1700
Data Index: 8551957 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.2160. Min Act: -0.1700
Data Index: 2959537 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.2160. Min Act: -0.1700
Data Index: 8218430 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.2160. Min Act: -0.1700
Data Index: 8218429 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.2160. Min Act: -0.1700
Data Index: 3625767 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.1847. Min Act: -0.1700
Data Index: 8079767 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.1222. Min Act: -0.1700
Data Index: 2852415 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.1535. Min Act: -0.1700
Data Index: 621815 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.1535. Min Act: -0.1700
Data Index: 855285 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.1535. Min Act: -0.1700
Data Index: 5389841 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.1535. Min Act: -0.1700
Data Index: 3338785 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.1535. Min Act: -0.1700
Data Index: 1333379 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5597. Min Range: -5.5597
Max Act: 5.1535. Min Act: -0.1700
Data Index: 4571480 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19