Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3586 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1237. Min Range: -4.1237
Max Act: 4.1237. Min Act: -0.1700
Data Index: 7881736 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.9675. Min Act: -0.1700
Data Index: 2877023 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.9675. Min Act: -0.1700
Data Index: 1304081 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.9675. Min Act: -0.1700
Data Index: 7513423 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.9049. Min Act: -0.1700
Data Index: 4939630 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.9049. Min Act: -0.1700
Data Index: 7570328 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.9049. Min Act: -0.1700
Data Index: 2361184 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.9049. Min Act: -0.1700
Data Index: 922726 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8737. Min Act: -0.1700
Data Index: 3873993 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8737. Min Act: -0.1700
Data Index: 7434432 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8737. Min Act: -0.1700
Data Index: 6900472 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8424. Min Act: -0.1700
Data Index: 7522005 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8424. Min Act: -0.1700
Data Index: 187998 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8424. Min Act: -0.1700
Data Index: 3670723 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8737. Min Act: -0.1700
Data Index: 1917489 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8424. Min Act: -0.1700
Data Index: 7894629 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8111. Min Act: -0.1700
Data Index: 1211000 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.7798. Min Act: -0.1700
Data Index: 730193 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8111. Min Act: -0.1700
Data Index: 1403903 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1237. Min Range: -4.1237
Max Act: 3.8111. Min Act: -0.1700
Data Index: 6603033 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19