Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1917 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.4127. Min Act: -0.1700
Data Index: 81989 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.3029. Min Act: -0.1700
Data Index: 5907994 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.2401. Min Act: -0.1700
Data Index: 8292166 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.2401. Min Act: -0.1700
Data Index: 6114253 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.2086. Min Act: -0.1700
Data Index: 4047894 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1615. Min Act: -0.1700
Data Index: 8193797 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1615. Min Act: -0.1700
Data Index: 4830473 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1615. Min Act: -0.1700
Data Index: 6760871 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1772. Min Act: -0.1700
Data Index: 2280253 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1772. Min Act: -0.1700
Data Index: 936854 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1772. Min Act: -0.1700
Data Index: 6423550 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1457. Min Act: -0.1700
Data Index: 4469159 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1772. Min Act: -0.1700
Data Index: 5239066 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1300. Min Act: -0.1700
Data Index: 1151699 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1300. Min Act: -0.1700
Data Index: 7516008 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1457. Min Act: -0.1700
Data Index: 4571323 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1615. Min Act: -0.1700
Data Index: 5252236 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1300. Min Act: -0.1700
Data Index: 3122330 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1300. Min Act: -0.1700
Data Index: 1990066 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4127. Min Range: -3.4127
Max Act: 3.1772. Min Act: -0.1700
Data Index: 7657771 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19