Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2638 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0888. Min Range: -8.0888
Max Act: 8.0888. Min Act: -0.1700
Data Index: 5329564 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0888. Min Range: -8.0888
Max Act: 8.0263. Min Act: -0.1700
Data Index: 8551080 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.9638. Min Act: -0.1700
Data Index: 4431868 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.9013. Min Act: -0.1700
Data Index: 152927 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.9013. Min Act: -0.1700
Data Index: 3609888 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.8075. Min Act: -0.1700
Data Index: 7999655 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.8075. Min Act: -0.1700
Data Index: 3385462 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.8388. Min Act: -0.1700
Data Index: 5727812 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.7763. Min Act: -0.1700
Data Index: 5270588 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.7763. Min Act: -0.1700
Data Index: 787750 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.7450. Min Act: -0.1700
Data Index: 2807172 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.6200. Min Act: -0.1700
Data Index: 2961272 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.6825. Min Act: -0.1700
Data Index: 2476552 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.7138. Min Act: -0.1700
Data Index: 1520860 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.7138. Min Act: -0.1700
Data Index: 6569400 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.6513. Min Act: -0.1700
Data Index: 4633285 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.6200. Min Act: -0.1700
Data Index: 4176517 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.6200. Min Act: -0.1700
Data Index: 3658113 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.6200. Min Act: -0.1700
Data Index: 6324434 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0888. Min Range: -8.0888
Max Act: 7.6513. Min Act: -0.1700
Data Index: 1024976 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19