Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4458 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.2398. Min Act: -0.1700
Data Index: 7203315 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.1455. Min Act: -0.1700
Data Index: 3775856 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.1140. Min Act: -0.1700
Data Index: 7914794 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.1297. Min Act: -0.1700
Data Index: 7753662 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.0667. Min Act: -0.1700
Data Index: 3173100 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.0824. Min Act: -0.1700
Data Index: 3173101 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.0035. Min Act: -0.1700
Data Index: 7237685 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.0193. Min Act: -0.1700
Data Index: 6583518 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.0193. Min Act: -0.1700
Data Index: 4423540 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.0351. Min Act: -0.1700
Data Index: 2008568 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2398. Min Range: -3.2398
Max Act: 3.0193. Min Act: -0.1700
Data Index: 5099181 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2398. Min Range: -3.2398
Max Act: 2.9877. Min Act: -0.1700
Data Index: 6562534 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2398. Min Range: -3.2398
Max Act: 2.9877. Min Act: -0.1700
Data Index: 1150325 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2398. Min Range: -3.2398
Max Act: 2.9877. Min Act: -0.1700
Data Index: 6636300 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2398. Min Range: -3.2398
Max Act: 2.9877. Min Act: -0.1700
Data Index: 2893175 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2398. Min Range: -3.2398
Max Act: 2.9877. Min Act: -0.1700
Data Index: 4647134 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2398. Min Range: -3.2398
Max Act: 2.9719. Min Act: -0.1700
Data Index: 7706486 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2398. Min Range: -3.2398
Max Act: 2.9719. Min Act: -0.1700
Data Index: 722293 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2398. Min Range: -3.2398
Max Act: 2.9402. Min Act: -0.1700
Data Index: 678733 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2398. Min Range: -3.2398
Max Act: 2.9561. Min Act: -0.1700
Data Index: 736102 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19