Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 26 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.5580. Min Act: -0.1696
Data Index: 6587840 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.5230. Min Act: -0.1700
Data Index: 2558970 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.5142. Min Act: -0.1697
Data Index: 2192309 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.5054. Min Act: -0.1700
Data Index: 7279342 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.5230. Min Act: -0.1687
Data Index: 2277401 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.5054. Min Act: -0.1672
Data Index: 4853554 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.5054. Min Act: -0.1687
Data Index: 1782025 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.5054. Min Act: -0.1700
Data Index: 3123310 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.5054. Min Act: -0.1700
Data Index: 3210189 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4879. Min Act: -0.1700
Data Index: 6587839 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4791. Min Act: -0.1694
Data Index: 1782024 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4791. Min Act: -0.1700
Data Index: 5242709 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4791. Min Act: -0.1700
Data Index: 4770429 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4791. Min Act: -0.1700
Data Index: 4247836 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4703. Min Act: -0.1697
Data Index: 4013455 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4791. Min Act: -0.1692
Data Index: 5499116 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4703. Min Act: -0.1700
Data Index: 3707060 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4791. Min Act: -0.1698
Data Index: 5301550 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4615. Min Act: -0.1700
Data Index: 5204475 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5580. Min Range: -1.5580
Max Act: 1.4615. Min Act: -0.1687
Data Index: 2927171 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19