Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5819 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2735. Min Range: -6.2735
Max Act: 6.2735. Min Act: -0.1700
Data Index: 7780895 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2735. Min Range: -6.2735
Max Act: 6.0860. Min Act: -0.1700
Data Index: 2836527 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.9610. Min Act: -0.1700
Data Index: 3265494 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.8985. Min Act: -0.1700
Data Index: 3826283 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.8360. Min Act: -0.1700
Data Index: 7197145 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.8048. Min Act: -0.1700
Data Index: 3546042 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.8048. Min Act: -0.1700
Data Index: 5796429 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.7735. Min Act: -0.1700
Data Index: 8506179 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.7735. Min Act: -0.1700
Data Index: 1359460 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.7735. Min Act: -0.1700
Data Index: 1473166 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.7423. Min Act: -0.1700
Data Index: 5866560 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.7110. Min Act: -0.1700
Data Index: 8062305 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.6798. Min Act: -0.1700
Data Index: 542350 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.6798. Min Act: -0.1700
Data Index: 646449 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.6485. Min Act: -0.1700
Data Index: 6311399 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.6485. Min Act: -0.1700
Data Index: 1812671 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.6485. Min Act: -0.1700
Data Index: 4736837 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.6173. Min Act: -0.1700
Data Index: 930055 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.6173. Min Act: -0.1700
Data Index: 216760 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2735. Min Range: -6.2735
Max Act: 5.6485. Min Act: -0.1700
Data Index: 7225733 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19