Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.4777. Min Act: -0.1700
Data Index: 7547819 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.4152. Min Act: -0.1700
Data Index: 3757184 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.3527. Min Act: -0.1700
Data Index: 5853743 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1964. Min Act: -0.1700
Data Index: 2280829 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1964. Min Act: -0.1700
Data Index: 4667836 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1652. Min Act: -0.1700
Data Index: 2727281 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1339. Min Act: -0.1700
Data Index: 5853744 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1339. Min Act: -0.1700
Data Index: 8209784 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1027. Min Act: -0.1700
Data Index: 7217628 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1339. Min Act: -0.1700
Data Index: 1903412 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.0714. Min Act: -0.1700
Data Index: 4466015 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.1027. Min Act: -0.1700
Data Index: 3621821 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.0714. Min Act: -0.1700
Data Index: 7006658 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.0714. Min Act: -0.1700
Data Index: 7855247 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.0402. Min Act: -0.1700
Data Index: 7051924 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.0089. Min Act: -0.1700
Data Index: 5029428 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.0089. Min Act: -0.1700
Data Index: 973217 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.0089. Min Act: -0.1700
Data Index: 5131847 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.0089. Min Act: -0.1700
Data Index: 467462 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4777. Min Range: -4.4777
Max Act: 4.0089. Min Act: -0.1700
Data Index: 3650386 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19