Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 857 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.2931. Min Act: -0.1700
Data Index: 1615906 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.2305. Min Act: -0.1700
Data Index: 7842183 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.2305. Min Act: -0.1700
Data Index: 551886 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.2305. Min Act: -0.1700
Data Index: 869342 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1993. Min Act: -0.1700
Data Index: 4800869 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1993. Min Act: -0.1700
Data Index: 8173655 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1680. Min Act: -0.1700
Data Index: 7431780 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1680. Min Act: -0.1700
Data Index: 3488673 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1680. Min Act: -0.1700
Data Index: 2499206 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1368. Min Act: -0.1700
Data Index: 4122824 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1368. Min Act: -0.1700
Data Index: 4917731 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1680. Min Act: -0.1700
Data Index: 4867687 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1368. Min Act: -0.1700
Data Index: 572321 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1680. Min Act: -0.1700
Data Index: 4542951 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1368. Min Act: -0.1700
Data Index: 7029602 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1055. Min Act: -0.1700
Data Index: 6123774 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1055. Min Act: -0.1700
Data Index: 2645413 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1055. Min Act: -0.1700
Data Index: 5141806 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1055. Min Act: -0.1700
Data Index: 3839046 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2931. Min Range: -4.2931
Max Act: 4.1055. Min Act: -0.1700
Data Index: 3510162 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19