Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3958 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.2470. Min Act: -0.1700
Data Index: 3808420 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.2157. Min Act: -0.1700
Data Index: 1020644 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.1845. Min Act: -0.1700
Data Index: 4741141 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.1532. Min Act: -0.1700
Data Index: 7370227 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.1532. Min Act: -0.1700
Data Index: 1221667 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.0595. Min Act: -0.1700
Data Index: 1488927 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.0595. Min Act: -0.1700
Data Index: 667792 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.0595. Min Act: -0.1700
Data Index: 4819925 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.0282. Min Act: -0.1700
Data Index: 2682305 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.0282. Min Act: -0.1700
Data Index: 7048810 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.0282. Min Act: -0.1700
Data Index: 1278268 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2470. Min Range: -5.2470
Max Act: 5.0282. Min Act: -0.1700
Data Index: 3265515 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2470. Min Range: -5.2470
Max Act: 4.9970. Min Act: -0.1700
Data Index: 4774775 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2470. Min Range: -5.2470
Max Act: 4.9970. Min Act: -0.1700
Data Index: 2485471 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2470. Min Range: -5.2470
Max Act: 4.9657. Min Act: -0.1700
Data Index: 3817466 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2470. Min Range: -5.2470
Max Act: 4.9970. Min Act: -0.1700
Data Index: 2048817 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2470. Min Range: -5.2470
Max Act: 4.9657. Min Act: -0.1700
Data Index: 2503578 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2470. Min Range: -5.2470
Max Act: 4.9657. Min Act: -0.1700
Data Index: 6133053 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2470. Min Range: -5.2470
Max Act: 4.9657. Min Act: -0.1700
Data Index: 4478388 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2470. Min Range: -5.2470
Max Act: 4.9657. Min Act: -0.1700
Data Index: 3502137 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19