Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4032 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4615. Min Range: -5.4615
Max Act: 5.4615. Min Act: -0.1700
Data Index: 142432 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4615. Min Range: -5.4615
Max Act: 5.0553. Min Act: -0.1700
Data Index: 8122105 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4615. Min Range: -5.4615
Max Act: 5.0553. Min Act: -0.1700
Data Index: 4812391 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.8990. Min Act: -0.1700
Data Index: 5684899 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.8365. Min Act: -0.1700
Data Index: 727945 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.8053. Min Act: -0.1700
Data Index: 6186379 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.7740. Min Act: -0.1700
Data Index: 4770997 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.7115. Min Act: -0.1700
Data Index: 5895640 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.6803. Min Act: -0.1700
Data Index: 3131640 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.7115. Min Act: -0.1700
Data Index: 7541258 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.6490. Min Act: -0.1700
Data Index: 3209893 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.6490. Min Act: -0.1700
Data Index: 4308093 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.6490. Min Act: -0.1700
Data Index: 4285869 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.6178. Min Act: -0.1700
Data Index: 4229761 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.6178. Min Act: -0.1700
Data Index: 2783635 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.6490. Min Act: -0.1700
Data Index: 252489 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.6178. Min Act: -0.1700
Data Index: 7551655 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.5865. Min Act: -0.1700
Data Index: 7763668 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.5865. Min Act: -0.1700
Data Index: 1427073 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4615. Min Range: -5.4615
Max Act: 4.5865. Min Act: -0.1700
Data Index: 6850883 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #19