Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2594 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.2191. Min Act: -0.1700
Data Index: 5702544 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.2025. Min Act: -0.1700
Data Index: 5721036 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.1859. Min Act: -0.1700
Data Index: 8735391 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.1693. Min Act: -0.1700
Data Index: 3960512 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.1360. Min Act: -0.1700
Data Index: 5047172 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.1527. Min Act: -0.1700
Data Index: 5380793 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.1527. Min Act: -0.1700
Data Index: 6710171 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.1193. Min Act: -0.1700
Data Index: 3498658 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.0858. Min Act: -0.1700
Data Index: 8259674 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.0690. Min Act: -0.1700
Data Index: 5131038 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.1025. Min Act: -0.1700
Data Index: 758052 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.0690. Min Act: -0.1700
Data Index: 6579746 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.1025. Min Act: -0.1700
Data Index: 3405016 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.0858. Min Act: -0.1700
Data Index: 7200289 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.0858. Min Act: -0.1700
Data Index: 3403239 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.0690. Min Act: -0.1700
Data Index: 4976370 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.0858. Min Act: -0.1700
Data Index: 4116289 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.0690. Min Act: -0.1700
Data Index: 2461070 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.0690. Min Act: -0.1700
Data Index: 2907125 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2191. Min Range: -2.2191
Max Act: 2.0522. Min Act: -0.1700
Data Index: 4272038 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19