Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4178 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.9262. Min Act: -0.1700
Data Index: 4119322 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.8323. Min Act: -0.1700
Data Index: 327778 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.7385. Min Act: -0.1700
Data Index: 816731 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.6760. Min Act: -0.1700
Data Index: 2428012 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.6290. Min Act: -0.1700
Data Index: 4571116 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5821. Min Act: -0.1700
Data Index: 7599448 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5821. Min Act: -0.1700
Data Index: 7086538 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5351. Min Act: -0.1700
Data Index: 8815118 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5351. Min Act: -0.1700
Data Index: 8313166 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5038. Min Act: -0.1700
Data Index: 6880840 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5351. Min Act: -0.1700
Data Index: 8550664 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5038. Min Act: -0.1700
Data Index: 8470147 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5038. Min Act: -0.1700
Data Index: 2122785 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5038. Min Act: -0.1700
Data Index: 314921 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5038. Min Act: -0.1700
Data Index: 1052147 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5038. Min Act: -0.1700
Data Index: 2663247 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5038. Min Act: -0.1700
Data Index: 3157261 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.5038. Min Act: -0.1700
Data Index: 3336535 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.4881. Min Act: -0.1700
Data Index: 2392013 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9262. Min Range: -3.9262
Max Act: 3.4724. Min Act: -0.1700
Data Index: 1765095 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19