Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4422 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.0399. Min Range: -5.0399
Max Act: 5.0399. Min Act: -0.1699
Data Index: 4258979 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.9774. Min Act: -0.1700
Data Index: 1451047 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.9149. Min Act: -0.1700
Data Index: 4020380 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.8837. Min Act: -0.1700
Data Index: 3092319 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.8837. Min Act: -0.1700
Data Index: 7452761 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.8212. Min Act: -0.1700
Data Index: 830981 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.8212. Min Act: -0.1700
Data Index: 6568515 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.8212. Min Act: -0.1699
Data Index: 1690525 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7899. Min Act: -0.1700
Data Index: 1068189 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7899. Min Act: -0.1700
Data Index: 5722938 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7899. Min Act: -0.1700
Data Index: 3001750 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7899. Min Act: -0.1699
Data Index: 7428499 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7899. Min Act: -0.1700
Data Index: 2612037 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7587. Min Act: -0.1700
Data Index: 6334179 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7587. Min Act: -0.1700
Data Index: 6185782 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7899. Min Act: -0.1692
Data Index: 2289982 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7587. Min Act: -0.1700
Data Index: 5998221 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7587. Min Act: -0.1700
Data Index: 982550 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7587. Min Act: -0.1696
Data Index: 3066732 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0399. Min Range: -5.0399
Max Act: 4.7587. Min Act: -0.1700
Data Index: 2048398 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19