Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1957 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.2653. Min Act: -0.1700
Data Index: 3434743 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.2323. Min Act: -0.1700
Data Index: 1568788 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1991. Min Act: -0.1700
Data Index: 7481312 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1991. Min Act: -0.1700
Data Index: 5680344 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1991. Min Act: -0.1700
Data Index: 4193678 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1825. Min Act: -0.1700
Data Index: 4332911 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1492. Min Act: -0.1700
Data Index: 954806 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1325. Min Act: -0.1700
Data Index: 6317986 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1492. Min Act: -0.1700
Data Index: 5311870 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1325. Min Act: -0.1700
Data Index: 1519883 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1492. Min Act: -0.1697
Data Index: 8668997 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1325. Min Act: -0.1700
Data Index: 7988773 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1325. Min Act: -0.1700
Data Index: 7059683 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1158. Min Act: -0.1700
Data Index: 1519880 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1158. Min Act: -0.1700
Data Index: 8799030 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.1158. Min Act: -0.1700
Data Index: 7067334 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.0991. Min Act: -0.1700
Data Index: 6668169 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.0991. Min Act: -0.1700
Data Index: 954807 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.0991. Min Act: -0.1700
Data Index: 5190303 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2653. Min Range: -2.2653
Max Act: 2.0823. Min Act: -0.1700
Data Index: 1951662 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19