Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 538 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.2602. Min Act: -0.1700
Data Index: 5148768 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.2602. Min Act: -0.1700
Data Index: 5527368 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1977. Min Act: -0.1700
Data Index: 8503599 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1977. Min Act: -0.1700
Data Index: 8481281 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1664. Min Act: -0.1700
Data Index: 307774 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1664. Min Act: -0.1700
Data Index: 2462045 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1664. Min Act: -0.1700
Data Index: 7923206 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1352. Min Act: -0.1700
Data Index: 8086363 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1352. Min Act: -0.1700
Data Index: 679122 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1039. Min Act: -0.1700
Data Index: 2145383 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1039. Min Act: -0.1700
Data Index: 5513229 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1039. Min Act: -0.1700
Data Index: 1734502 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1039. Min Act: -0.1700
Data Index: 153376 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1039. Min Act: -0.1700
Data Index: 3511832 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1352. Min Act: -0.1700
Data Index: 7360996 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1039. Min Act: -0.1700
Data Index: 2900095 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1352. Min Act: -0.1700
Data Index: 6850343 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1039. Min Act: -0.1700
Data Index: 2698255 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.0727. Min Act: -0.1700
Data Index: 1059487 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2602. Min Range: -5.2602
Max Act: 5.1039. Min Act: -0.1700
Data Index: 1940878 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19