Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2179 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.4580. Min Act: -0.1700
Data Index: 1215051 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.5205. Min Act: -0.1700
Data Index: 5927456 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.4892. Min Act: -0.1700
Data Index: 2853103 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.4892. Min Act: -0.1700
Data Index: 5022865 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.4267. Min Act: -0.1700
Data Index: 6735015 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 1155828 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3954. Min Act: -0.1700
Data Index: 679812 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3954. Min Act: -0.1700
Data Index: 4054093 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3954. Min Act: -0.1700
Data Index: 2732303 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3954. Min Act: -0.1700
Data Index: 192556 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3954. Min Act: -0.1700
Data Index: 5280458 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 1479448 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 7476238 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3329. Min Act: -0.1700
Data Index: 8689691 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 6232900 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3329. Min Act: -0.1700
Data Index: 912716 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3329. Min Act: -0.1700
Data Index: 8560230 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3642. Min Act: -0.1700
Data Index: 5062812 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.3017. Min Act: -0.1700
Data Index: 1113122 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5205. Min Range: -4.5205
Max Act: 4.2704. Min Act: -0.1700
Data Index: 1729333 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19