Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3227. Min Range: -6.3227
Max Act: 6.3227. Min Act: -0.1700
Data Index: 6625503 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3227. Min Range: -6.3227
Max Act: 6.0102. Min Act: -0.1700
Data Index: 1073196 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3227. Min Range: -6.3227
Max Act: 6.0102. Min Act: -0.1700
Data Index: 5212454 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.9789. Min Act: -0.1700
Data Index: 1297366 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.9789. Min Act: -0.1700
Data Index: 972205 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.8852. Min Act: -0.1700
Data Index: 6813473 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.8539. Min Act: -0.1700
Data Index: 7234775 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.7289. Min Act: -0.1700
Data Index: 8506491 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.7289. Min Act: -0.1700
Data Index: 2472548 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.6977. Min Act: -0.1700
Data Index: 507815 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.7289. Min Act: -0.1700
Data Index: 3238931 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.6664. Min Act: -0.1700
Data Index: 656708 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.6977. Min Act: -0.1700
Data Index: 1042486 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.6664. Min Act: -0.1700
Data Index: 736850 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.6664. Min Act: -0.1700
Data Index: 4686033 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.6352. Min Act: -0.1700
Data Index: 1313491 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.6352. Min Act: -0.1700
Data Index: 6588799 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.6039. Min Act: -0.1700
Data Index: 3523577 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.6039. Min Act: -0.1700
Data Index: 4345752 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3227. Min Range: -6.3227
Max Act: 5.6039. Min Act: -0.1700
Data Index: 6903350 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19