Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3919 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0172. Min Range: -6.0172
Max Act: 6.0172. Min Act: -0.1700
Data Index: 7714752 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.7359. Min Act: -0.1700
Data Index: 107187 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.7359. Min Act: -0.1700
Data Index: 390787 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.7047. Min Act: -0.1700
Data Index: 1787442 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.6109. Min Act: -0.1700
Data Index: 6419881 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.5797. Min Act: -0.1700
Data Index: 3546055 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.5484. Min Act: -0.1700
Data Index: 3158530 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.4859. Min Act: -0.1700
Data Index: 2578681 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.5172. Min Act: -0.1700
Data Index: 941787 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.3922. Min Act: -0.1700
Data Index: 5268921 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.4234. Min Act: -0.1700
Data Index: 506055 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.3922. Min Act: -0.1700
Data Index: 7036983 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.3922. Min Act: -0.1700
Data Index: 8062152 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.3922. Min Act: -0.1700
Data Index: 5421345 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.3922. Min Act: -0.1700
Data Index: 3354512 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.3922. Min Act: -0.1700
Data Index: 2460962 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.3922. Min Act: -0.1700
Data Index: 5277573 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.3609. Min Act: -0.1700
Data Index: 4318752 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.3609. Min Act: -0.1700
Data Index: 3063754 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0172. Min Range: -6.0172
Max Act: 5.3297. Min Act: -0.1700
Data Index: 1275593 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19