Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1462. Min Range: -6.1462
Max Act: 6.1462. Min Act: -0.1700
Data Index: 4461868 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.8024. Min Act: -0.1700
Data Index: 2685748 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.6774. Min Act: -0.1700
Data Index: 5295865 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.6149. Min Act: -0.1700
Data Index: 6733772 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.6462. Min Act: -0.1700
Data Index: 4960968 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.6149. Min Act: -0.1700
Data Index: 1898616 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.5837. Min Act: -0.1700
Data Index: 786952 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.5524. Min Act: -0.1700
Data Index: 422706 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.5524. Min Act: -0.1700
Data Index: 7225081 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.5212. Min Act: -0.1700
Data Index: 7494453 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.5212. Min Act: -0.1700
Data Index: 7947361 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4899. Min Act: -0.1700
Data Index: 4057426 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4587. Min Act: -0.1700
Data Index: 2997026 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4274. Min Act: -0.1700
Data Index: 6215187 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4274. Min Act: -0.1700
Data Index: 3730846 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.4274. Min Act: -0.1700
Data Index: 2612339 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.3962. Min Act: -0.1700
Data Index: 4604183 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.3962. Min Act: -0.1700
Data Index: 3854553 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.3649. Min Act: -0.1700
Data Index: 2126054 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1462. Min Range: -6.1462
Max Act: 5.3649. Min Act: -0.1700
Data Index: 127796 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19