Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1482 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2470. Min Range: -6.2470
Max Act: 6.2470. Min Act: -0.1700
Data Index: 8156517 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2470. Min Range: -6.2470
Max Act: 6.0282. Min Act: -0.1700
Data Index: 4852524 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.9657. Min Act: -0.1700
Data Index: 1899254 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.8720. Min Act: -0.1700
Data Index: 3576273 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.7782. Min Act: -0.1700
Data Index: 6251150 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.7157. Min Act: -0.1700
Data Index: 3886190 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.6845. Min Act: -0.1700
Data Index: 3751475 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.7157. Min Act: -0.1700
Data Index: 3817736 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.6845. Min Act: -0.1700
Data Index: 862118 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.7157. Min Act: -0.1700
Data Index: 5005639 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.6220. Min Act: -0.1700
Data Index: 5660964 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.6532. Min Act: -0.1700
Data Index: 3122500 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.6532. Min Act: -0.1700
Data Index: 793484 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.6845. Min Act: -0.1700
Data Index: 8016771 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.6532. Min Act: -0.1700
Data Index: 3113705 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.6220. Min Act: -0.1700
Data Index: 3058374 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.6220. Min Act: -0.1700
Data Index: 137435 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.5595. Min Act: -0.1700
Data Index: 418872 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.5907. Min Act: -0.1700
Data Index: 778638 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2470. Min Range: -6.2470
Max Act: 5.5595. Min Act: -0.1700
Data Index: 7109175 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19