Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3542 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.5096. Min Act: -0.1700
Data Index: 5015548 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.4393. Min Act: -0.1700
Data Index: 8646233 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.3335. Min Act: -0.1700
Data Index: 5015549 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1925. Min Act: -0.1700
Data Index: 4761296 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.2101. Min Act: -0.1700
Data Index: 5928114 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1749. Min Act: -0.1700
Data Index: 6745524 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1222. Min Act: -0.1700
Data Index: 5057957 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1222. Min Act: -0.1700
Data Index: 5741682 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1397. Min Act: -0.1700
Data Index: 401307 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1222. Min Act: -0.1700
Data Index: 7999275 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1222. Min Act: -0.1700
Data Index: 5732561 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1222. Min Act: -0.1700
Data Index: 5704778 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1222. Min Act: -0.1700
Data Index: 4750375 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1222. Min Act: -0.1700
Data Index: 401305 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1046. Min Act: -0.1700
Data Index: 1796342 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1046. Min Act: -0.1700
Data Index: 7479010 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1046. Min Act: -0.1700
Data Index: 3040331 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1046. Min Act: -0.1700
Data Index: 4753877 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.1046. Min Act: -0.1700
Data Index: 7827651 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5096. Min Range: -1.5096
Max Act: 1.0871. Min Act: -0.1700
Data Index: 5014889 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19