Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3218 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3417. Min Range: -4.3417
Max Act: 4.3417. Min Act: -0.1700
Data Index: 531944 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3417. Min Range: -4.3417
Max Act: 4.1542. Min Act: -0.1700
Data Index: 8787043 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3417. Min Range: -4.3417
Max Act: 4.1229. Min Act: -0.1700
Data Index: 2142808 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3417. Min Range: -4.3417
Max Act: 4.0917. Min Act: -0.1700
Data Index: 3210558 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3417. Min Range: -4.3417
Max Act: 4.0604. Min Act: -0.1700
Data Index: 4193046 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3417. Min Range: -4.3417
Max Act: 4.0291. Min Act: -0.1700
Data Index: 8383397 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3417. Min Range: -4.3417
Max Act: 4.0604. Min Act: -0.1700
Data Index: 6536709 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3417. Min Range: -4.3417
Max Act: 4.0291. Min Act: -0.1700
Data Index: 4930118 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3417. Min Range: -4.3417
Max Act: 4.0291. Min Act: -0.1700
Data Index: 2305931 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.9979. Min Act: -0.1700
Data Index: 5645451 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.9979. Min Act: -0.1700
Data Index: 8016937 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.9979. Min Act: -0.1700
Data Index: 7257659 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.9979. Min Act: -0.1700
Data Index: 1183798 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.9666. Min Act: -0.1700
Data Index: 7103953 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.9666. Min Act: -0.1700
Data Index: 4442070 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.9666. Min Act: -0.1700
Data Index: 5983706 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.9354. Min Act: -0.1700
Data Index: 4703109 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.9354. Min Act: -0.1700
Data Index: 5528784 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.8728. Min Act: -0.1700
Data Index: 2839815 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3417. Min Range: -4.3417
Max Act: 3.9041. Min Act: -0.1700
Data Index: 3670960 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19