Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 428 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1087. Min Range: -9.1087
Max Act: 9.1087. Min Act: -0.1700
Data Index: 2968581 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1087. Min Range: -9.1087
Max Act: 8.2337. Min Act: -0.1700
Data Index: 6857952 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1087. Min Range: -9.1087
Max Act: 8.1712. Min Act: -0.1700
Data Index: 8376669 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1087. Min Range: -9.1087
Max Act: 8.1712. Min Act: -0.1700
Data Index: 7117064 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1087. Min Range: -9.1087
Max Act: 8.1712. Min Act: -0.1700
Data Index: 5082219 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1087. Min Range: -9.1087
Max Act: 8.1087. Min Act: -0.1700
Data Index: 1853908 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.9212. Min Act: -0.1700
Data Index: 6206578 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.9212. Min Act: -0.1700
Data Index: 2075944 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.9212. Min Act: -0.1700
Data Index: 4290957 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.8587. Min Act: -0.1700
Data Index: 1121924 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.8587. Min Act: -0.1700
Data Index: 4574546 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.9212. Min Act: -0.1700
Data Index: 1966611 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.7650. Min Act: -0.1700
Data Index: 4786230 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.7650. Min Act: -0.1700
Data Index: 3394888 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.7650. Min Act: -0.1700
Data Index: 939615 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.7337. Min Act: -0.1700
Data Index: 4751814 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.7025. Min Act: -0.1700
Data Index: 2373476 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.7025. Min Act: -0.1700
Data Index: 1903670 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.7025. Min Act: -0.1700
Data Index: 848693 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1087. Min Range: -9.1087
Max Act: 7.6712. Min Act: -0.1700
Data Index: 2623357 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #19