Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3667 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7956. Min Act: -0.1700
Data Index: 1298501 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7644. Min Act: -0.1700
Data Index: 3515541 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7956. Min Act: -0.1700
Data Index: 8264641 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7644. Min Act: -0.1700
Data Index: 7257118 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7331. Min Act: -0.1700
Data Index: 7178169 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7331. Min Act: -0.1700
Data Index: 1650391 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7331. Min Act: -0.1700
Data Index: 2474406 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7331. Min Act: -0.1700
Data Index: 785322 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7331. Min Act: -0.1700
Data Index: 944101 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7019. Min Act: -0.1700
Data Index: 4330813 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.6706. Min Act: -0.1700
Data Index: 2861013 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7019. Min Act: -0.1700
Data Index: 5782789 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.7019. Min Act: -0.1700
Data Index: 8601187 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.6706. Min Act: -0.1700
Data Index: 7506366 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.6706. Min Act: -0.1700
Data Index: 153212 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.6706. Min Act: -0.1700
Data Index: 4785693 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.6394. Min Act: -0.1700
Data Index: 6430633 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.6394. Min Act: -0.1700
Data Index: 2207002 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.6394. Min Act: -0.1700
Data Index: 2101197 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7956. Min Range: -4.7956
Max Act: 4.6394. Min Act: -0.1700
Data Index: 2991105 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19