Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3497 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7537. Min Act: -0.1700
Data Index: 4761751 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7364. Min Act: -0.1700
Data Index: 2314401 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7277. Min Act: -0.1700
Data Index: 1129920 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7277. Min Act: -0.1700
Data Index: 1343819 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7018. Min Act: -0.1700
Data Index: 7238926 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7191. Min Act: -0.1700
Data Index: 4433688 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6931. Min Act: -0.1700
Data Index: 8154346 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7018. Min Act: -0.1700
Data Index: 5117326 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6844. Min Act: -0.1700
Data Index: 621543 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.7018. Min Act: -0.1699
Data Index: 5842981 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6757. Min Act: -0.1700
Data Index: 4711583 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6931. Min Act: -0.1700
Data Index: 1447975 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6844. Min Act: -0.1700
Data Index: 7190106 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6757. Min Act: -0.1700
Data Index: 6118203 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6670. Min Act: -0.1700
Data Index: 6720029 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6757. Min Act: -0.1700
Data Index: 3183672 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6670. Min Act: -0.1700
Data Index: 4623728 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6670. Min Act: -0.1700
Data Index: 338418 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6583. Min Act: -0.1700
Data Index: 2455426 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7537. Min Range: -1.7537
Max Act: 1.6583. Min Act: -0.1700
Data Index: 3413125 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19