Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 60 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.7634. Min Act: -0.1700
Data Index: 5421977 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.5759. Min Act: -0.1700
Data Index: 2972254 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.5446. Min Act: -0.1700
Data Index: 3099884 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.3884. Min Act: -0.1700
Data Index: 1183953 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.3884. Min Act: -0.1700
Data Index: 4796993 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.3571. Min Act: -0.1700
Data Index: 4114672 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.3259. Min Act: -0.1700
Data Index: 8538993 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.3259. Min Act: -0.1700
Data Index: 2498802 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.2946. Min Act: -0.1700
Data Index: 4183129 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.2946. Min Act: -0.1700
Data Index: 3368210 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.2634. Min Act: -0.1700
Data Index: 6592314 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.2634. Min Act: -0.1700
Data Index: 91593 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.2634. Min Act: -0.1700
Data Index: 7357203 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.2009. Min Act: -0.1700
Data Index: 6420526 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.1696. Min Act: -0.1700
Data Index: 1841195 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.2009. Min Act: -0.1700
Data Index: 560443 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.1696. Min Act: -0.1700
Data Index: 7836440 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.1071. Min Act: -0.1700
Data Index: 5485085 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.1071. Min Act: -0.1700
Data Index: 3597477 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7634. Min Range: -6.7634
Max Act: 6.1071. Min Act: -0.1700
Data Index: 6945361 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19