Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.7884. Min Act: -0.1700
Data Index: 7294706 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.4759. Min Act: -0.1700
Data Index: 4151770 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.4134. Min Act: -0.1700
Data Index: 4231689 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.4134. Min Act: -0.1700
Data Index: 4019888 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.3509. Min Act: -0.1700
Data Index: 1758449 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.3509. Min Act: -0.1700
Data Index: 2623090 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.3509. Min Act: -0.1700
Data Index: 466555 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.2572. Min Act: -0.1700
Data Index: 2855201 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.2259. Min Act: -0.1700
Data Index: 617290 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.2884. Min Act: -0.1700
Data Index: 2870856 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.2259. Min Act: -0.1700
Data Index: 5708223 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.2572. Min Act: -0.1700
Data Index: 5292318 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.2259. Min Act: -0.1700
Data Index: 7245849 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.1947. Min Act: -0.1700
Data Index: 5040601 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.1634. Min Act: -0.1700
Data Index: 7626102 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.1634. Min Act: -0.1700
Data Index: 5947045 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.1634. Min Act: -0.1700
Data Index: 8641621 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.1634. Min Act: -0.1700
Data Index: 8159961 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.1322. Min Act: -0.1700
Data Index: 2819853 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7884. Min Range: -6.7884
Max Act: 6.1009. Min Act: -0.1700
Data Index: 8127824 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19