Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1603 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.5295. Min Act: -0.1700
Data Index: 4345488 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.5032. Min Act: -0.1700
Data Index: 8627153 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4856. Min Act: -0.1700
Data Index: 3481569 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4856. Min Act: -0.1700
Data Index: 4699221 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4944. Min Act: -0.1700
Data Index: 3586586 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4856. Min Act: -0.1700
Data Index: 1967463 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4768. Min Act: -0.1700
Data Index: 4971140 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4768. Min Act: -0.1700
Data Index: 7968649 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4856. Min Act: -0.1700
Data Index: 5464463 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4768. Min Act: -0.1700
Data Index: 760937 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4680. Min Act: -0.1693
Data Index: 6145614 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4592. Min Act: -0.1698
Data Index: 4497521 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4416. Min Act: -0.1700
Data Index: 5717500 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4504. Min Act: -0.1700
Data Index: 2733884 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4504. Min Act: -0.1700
Data Index: 7984376 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4416. Min Act: -0.1700
Data Index: 3795499 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4504. Min Act: -0.1700
Data Index: 1714939 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4416. Min Act: -0.1700
Data Index: 2734113 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4416. Min Act: -0.1700
Data Index: 2388429 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5295. Min Range: -1.5295
Max Act: 1.4328. Min Act: -0.1698
Data Index: 4357912 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19