Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 327 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.8928. Min Act: -0.1700
Data Index: 4925799 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.8302. Min Act: -0.1700
Data Index: 5897909 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.8615. Min Act: -0.1700
Data Index: 5315010 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.7677. Min Act: -0.1700
Data Index: 7692416 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.7364. Min Act: -0.1700
Data Index: 3964793 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.7051. Min Act: -0.1700
Data Index: 7692417 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.7051. Min Act: -0.1700
Data Index: 7903785 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.7051. Min Act: -0.1700
Data Index: 5183392 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6738. Min Act: -0.1700
Data Index: 1363452 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6738. Min Act: -0.1700
Data Index: 6307370 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6425. Min Act: -0.1700
Data Index: 127959 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6425. Min Act: -0.1700
Data Index: 7580077 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6425. Min Act: -0.1700
Data Index: 6664570 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6425. Min Act: -0.1700
Data Index: 5796952 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6112. Min Act: -0.1700
Data Index: 5851191 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6112. Min Act: -0.1700
Data Index: 1246908 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.5643. Min Act: -0.1700
Data Index: 6648920 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6112. Min Act: -0.1700
Data Index: 3017100 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6112. Min Act: -0.1700
Data Index: 249951 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8928. Min Range: -3.8928
Max Act: 3.6112. Min Act: -0.1700
Data Index: 3341303 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19