Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1750 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.5106. Min Act: -0.1700
Data Index: 3205120 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.2606. Min Act: -0.1700
Data Index: 4950602 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.2293. Min Act: -0.1700
Data Index: 8267737 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.2293. Min Act: -0.1700
Data Index: 2896475 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1981. Min Act: -0.1700
Data Index: 8364932 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1356. Min Act: -0.1700
Data Index: 414335 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1043. Min Act: -0.1700
Data Index: 3474982 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1043. Min Act: -0.1700
Data Index: 2053911 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1043. Min Act: -0.1700
Data Index: 5047792 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1043. Min Act: -0.1700
Data Index: 7396561 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0731. Min Act: -0.1700
Data Index: 353153 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0731. Min Act: -0.1700
Data Index: 618741 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1043. Min Act: -0.1700
Data Index: 6969944 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0731. Min Act: -0.1700
Data Index: 5457670 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0418. Min Act: -0.1700
Data Index: 4583855 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0418. Min Act: -0.1700
Data Index: 3176062 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0418. Min Act: -0.1700
Data Index: 3930109 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0418. Min Act: -0.1700
Data Index: 4984886 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0106. Min Act: -0.1700
Data Index: 756338 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5106. Min Range: -5.5106
Max Act: 4.9793. Min Act: -0.1700
Data Index: 6661353 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19