Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1197 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.4356. Min Act: -0.1700
Data Index: 1603444 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.4356. Min Act: -0.1700
Data Index: 2278225 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.4043. Min Act: -0.1700
Data Index: 5656495 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.3418. Min Act: -0.1700
Data Index: 2085608 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.3418. Min Act: -0.1700
Data Index: 8748357 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.3106. Min Act: -0.1700
Data Index: 2871024 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.3106. Min Act: -0.1700
Data Index: 6938620 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2793. Min Act: -0.1700
Data Index: 1984953 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.3418. Min Act: -0.1700
Data Index: 4396752 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2793. Min Act: -0.1700
Data Index: 2547558 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2481. Min Act: -0.1700
Data Index: 2619386 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2793. Min Act: -0.1700
Data Index: 5751922 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2793. Min Act: -0.1700
Data Index: 14224 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2793. Min Act: -0.1700
Data Index: 981482 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2793. Min Act: -0.1700
Data Index: 8500947 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2793. Min Act: -0.1700
Data Index: 3631396 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2481. Min Act: -0.1700
Data Index: 3544844 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2481. Min Act: -0.1700
Data Index: 4567084 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2481. Min Act: -0.1700
Data Index: 5367733 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4356. Min Range: -5.4356
Max Act: 5.2481. Min Act: -0.1700
Data Index: 5675370 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19