Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4830 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3760. Min Range: -6.3760
Max Act: 6.3760. Min Act: -0.1700
Data Index: 6535475 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3760. Min Range: -6.3760
Max Act: 6.1260. Min Act: -0.1700
Data Index: 4092384 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3760. Min Range: -6.3760
Max Act: 6.0322. Min Act: -0.1700
Data Index: 7841467 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.9385. Min Act: -0.1700
Data Index: 1117762 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.9385. Min Act: -0.1700
Data Index: 3545823 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.9385. Min Act: -0.1700
Data Index: 4861207 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.9385. Min Act: -0.1700
Data Index: 7847463 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.9072. Min Act: -0.1700
Data Index: 702703 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.9072. Min Act: -0.1700
Data Index: 5583227 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.9072. Min Act: -0.1700
Data Index: 7939211 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.8760. Min Act: -0.1700
Data Index: 5091331 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.8760. Min Act: -0.1700
Data Index: 1380850 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.8760. Min Act: -0.1700
Data Index: 6421627 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.8760. Min Act: -0.1700
Data Index: 1873873 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.8760. Min Act: -0.1700
Data Index: 862129 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.8447. Min Act: -0.1700
Data Index: 795871 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.8447. Min Act: -0.1700
Data Index: 3305372 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.8447. Min Act: -0.1700
Data Index: 2534631 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.8135. Min Act: -0.1700
Data Index: 8190717 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3760. Min Range: -6.3760
Max Act: 5.8135. Min Act: -0.1700
Data Index: 4056606 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19