Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3387 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.2161. Min Act: -0.1700
Data Index: 5848494 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.1163. Min Act: -0.1700
Data Index: 8352756 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.1163. Min Act: -0.1700
Data Index: 7208834 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.1163. Min Act: -0.1700
Data Index: 6578567 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0828. Min Act: -0.1700
Data Index: 2765135 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0828. Min Act: -0.1700
Data Index: 4690605 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0323. Min Act: -0.1700
Data Index: 3463986 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0492. Min Act: -0.1692
Data Index: 3463994 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0155. Min Act: -0.1700
Data Index: 634253 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0492. Min Act: -0.1700
Data Index: 634252 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0155. Min Act: -0.1700
Data Index: 6612306 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0155. Min Act: -0.1700
Data Index: 3009912 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0323. Min Act: -0.1700
Data Index: 6299118 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0323. Min Act: -0.1700
Data Index: 3464013 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0155. Min Act: -0.1700
Data Index: 3463979 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0155. Min Act: -0.1698
Data Index: 3464004 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0155. Min Act: -0.1698
Data Index: 3464007 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0155. Min Act: -0.1700
Data Index: 3216219 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0323. Min Act: -0.1700
Data Index: 3464005 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2161. Min Range: -2.2161
Max Act: 2.0155. Min Act: -0.1687
Data Index: 511107 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19