Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3688 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.5466. Min Act: -0.1700
Data Index: 2171221 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.3591. Min Act: -0.1700
Data Index: 3687412 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.3904. Min Act: -0.1700
Data Index: 553925 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.3591. Min Act: -0.1700
Data Index: 977095 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.3279. Min Act: -0.1700
Data Index: 7944472 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.3279. Min Act: -0.1700
Data Index: 7662739 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2966. Min Act: -0.1700
Data Index: 633448 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.3591. Min Act: -0.1700
Data Index: 8375436 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2654. Min Act: -0.1700
Data Index: 4020672 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2341. Min Act: -0.1700
Data Index: 6831676 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2029. Min Act: -0.1700
Data Index: 1253315 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2341. Min Act: -0.1700
Data Index: 4882076 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2029. Min Act: -0.1700
Data Index: 381144 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2654. Min Act: -0.1700
Data Index: 5221508 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2341. Min Act: -0.1700
Data Index: 1750296 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.1716. Min Act: -0.1700
Data Index: 1319582 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2341. Min Act: -0.1700
Data Index: 5653777 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2029. Min Act: -0.1700
Data Index: 3778517 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2029. Min Act: -0.1700
Data Index: 7990140 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5466. Min Range: -5.5466
Max Act: 5.2029. Min Act: -0.1700
Data Index: 5047668 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19