Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1455 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1296. Min Range: -5.1296
Max Act: 5.1296. Min Act: -0.1700
Data Index: 68720 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1296. Min Range: -5.1296
Max Act: 5.1296. Min Act: -0.1700
Data Index: 6008875 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1296. Min Range: -5.1296
Max Act: 5.0984. Min Act: -0.1700
Data Index: 4406684 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1296. Min Range: -5.1296
Max Act: 5.0671. Min Act: -0.1700
Data Index: 6268319 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1296. Min Range: -5.1296
Max Act: 5.0359. Min Act: -0.1700
Data Index: 6843043 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1296. Min Range: -5.1296
Max Act: 5.0359. Min Act: -0.1700
Data Index: 8067825 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1296. Min Range: -5.1296
Max Act: 5.0046. Min Act: -0.1700
Data Index: 5986053 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.9421. Min Act: -0.1700
Data Index: 7880551 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.8796. Min Act: -0.1700
Data Index: 3704355 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.8484. Min Act: -0.1700
Data Index: 2782022 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.8171. Min Act: -0.1700
Data Index: 481335 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.7546. Min Act: -0.1700
Data Index: 2100648 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.7546. Min Act: -0.1700
Data Index: 6566598 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.6921. Min Act: -0.1700
Data Index: 7116754 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.7234. Min Act: -0.1700
Data Index: 3475127 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.6921. Min Act: -0.1700
Data Index: 2274586 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.6921. Min Act: -0.1700
Data Index: 5124254 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.6921. Min Act: -0.1700
Data Index: 5445379 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.6609. Min Act: -0.1700
Data Index: 4973039 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1296. Min Range: -5.1296
Max Act: 4.6609. Min Act: -0.1700
Data Index: 8427746 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19