Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 256 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3258. Min Range: -6.3258
Max Act: 6.3258. Min Act: -0.1700
Data Index: 326339 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3258. Min Range: -6.3258
Max Act: 6.0133. Min Act: -0.1700
Data Index: 756678 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.9820. Min Act: -0.1700
Data Index: 3238049 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.9195. Min Act: -0.1700
Data Index: 3703760 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.8570. Min Act: -0.1700
Data Index: 8367924 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.8258. Min Act: -0.1700
Data Index: 7359586 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.8258. Min Act: -0.1700
Data Index: 418615 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.7633. Min Act: -0.1700
Data Index: 3238054 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.7945. Min Act: -0.1700
Data Index: 7813402 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.7633. Min Act: -0.1700
Data Index: 5714655 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.7945. Min Act: -0.1700
Data Index: 6389875 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.7008. Min Act: -0.1700
Data Index: 2441411 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.6070. Min Act: -0.1700
Data Index: 428652 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.6695. Min Act: -0.1700
Data Index: 1465314 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.6695. Min Act: -0.1700
Data Index: 418584 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.5758. Min Act: -0.1700
Data Index: 3597728 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.5445. Min Act: -0.1700
Data Index: 3837741 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.6070. Min Act: -0.1700
Data Index: 7338589 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.5758. Min Act: -0.1700
Data Index: 6987952 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3258. Min Range: -6.3258
Max Act: 5.5133. Min Act: -0.1700
Data Index: 4791385 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19