Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2485 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1380. Min Range: -5.1380
Max Act: 5.1380. Min Act: -0.1700
Data Index: 1873854 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1380. Min Range: -5.1380
Max Act: 5.1380. Min Act: -0.1699
Data Index: 624465 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1380. Min Range: -5.1380
Max Act: 5.1068. Min Act: -0.1700
Data Index: 1029392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1380. Min Range: -5.1380
Max Act: 5.0755. Min Act: -0.1690
Data Index: 2195918 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1380. Min Range: -5.1380
Max Act: 5.0755. Min Act: -0.1700
Data Index: 6117566 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9818. Min Act: -0.1700
Data Index: 3191374 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9818. Min Act: -0.1700
Data Index: 2892490 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1380. Min Range: -5.1380
Max Act: 5.0130. Min Act: -0.1700
Data Index: 876730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9505. Min Act: -0.1700
Data Index: 758017 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9505. Min Act: -0.1700
Data Index: 5540278 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9505. Min Act: -0.1693
Data Index: 6672702 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9505. Min Act: -0.1700
Data Index: 7166991 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9193. Min Act: -0.1700
Data Index: 1078393 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9193. Min Act: -0.1699
Data Index: 4098549 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9193. Min Act: -0.1638
Data Index: 6900758 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9193. Min Act: -0.1700
Data Index: 6624719 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9193. Min Act: -0.1699
Data Index: 5759441 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.9193. Min Act: -0.1699
Data Index: 1339306 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.8880. Min Act: -0.1700
Data Index: 2089685 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1380. Min Range: -5.1380
Max Act: 4.8880. Min Act: -0.1700
Data Index: 5136920 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19