Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3710 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.7109. Min Act: -0.1700
Data Index: 398678 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.6172. Min Act: -0.1700
Data Index: 3952243 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.5547. Min Act: -0.1700
Data Index: 487872 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.5234. Min Act: -0.1700
Data Index: 6246106 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.4609. Min Act: -0.1700
Data Index: 1582973 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.3359. Min Act: -0.1700
Data Index: 4839371 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.2734. Min Act: -0.1700
Data Index: 3607080 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.2734. Min Act: -0.1700
Data Index: 1601116 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.2734. Min Act: -0.1700
Data Index: 6830149 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.2422. Min Act: -0.1700
Data Index: 6844282 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.2422. Min Act: -0.1700
Data Index: 4868110 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.2422. Min Act: -0.1700
Data Index: 43823 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.1797. Min Act: -0.1700
Data Index: 330407 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.1797. Min Act: -0.1700
Data Index: 2180569 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.1797. Min Act: -0.1700
Data Index: 3731941 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.1484. Min Act: -0.1700
Data Index: 909028 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.1484. Min Act: -0.1700
Data Index: 4818721 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.1484. Min Act: -0.1700
Data Index: 7231939 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.0859. Min Act: -0.1700
Data Index: 2296741 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7109. Min Range: -5.7109
Max Act: 5.0859. Min Act: -0.1700
Data Index: 1271600 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19