Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1301 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1035. Min Range: -6.1035
Max Act: 6.1035. Min Act: -0.1700
Data Index: 1328729 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1035. Min Range: -6.1035
Max Act: 6.0723. Min Act: -0.1700
Data Index: 5825281 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1035. Min Range: -6.1035
Max Act: 6.0410. Min Act: -0.1700
Data Index: 1174754 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.9785. Min Act: -0.1700
Data Index: 2318708 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.9160. Min Act: -0.1700
Data Index: 1436277 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.6348. Min Act: -0.1700
Data Index: 644219 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.6660. Min Act: -0.1700
Data Index: 5766064 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.6660. Min Act: -0.1700
Data Index: 1458707 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.6348. Min Act: -0.1700
Data Index: 2418719 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.6035. Min Act: -0.1700
Data Index: 3021263 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.5723. Min Act: -0.1700
Data Index: 728850 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.5723. Min Act: -0.1700
Data Index: 210307 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.4785. Min Act: -0.1700
Data Index: 7380719 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.5098. Min Act: -0.1700
Data Index: 6878378 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.4785. Min Act: -0.1700
Data Index: 3367651 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.4473. Min Act: -0.1700
Data Index: 7454481 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.4160. Min Act: -0.1700
Data Index: 1482066 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.4473. Min Act: -0.1700
Data Index: 5111419 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.4785. Min Act: -0.1700
Data Index: 371370 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1035. Min Range: -6.1035
Max Act: 5.4473. Min Act: -0.1700
Data Index: 8143672 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19