Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 844 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8993. Min Act: -0.1700
Data Index: 6509076 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.9151. Min Act: -0.1700
Data Index: 5354547 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.9151. Min Act: -0.1700
Data Index: 5676654 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.9151. Min Act: -0.1700
Data Index: 6198223 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.9151. Min Act: -0.1700
Data Index: 4380956 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8834. Min Act: -0.1700
Data Index: 7467834 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8834. Min Act: -0.1700
Data Index: 4380957 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8675. Min Act: -0.1700
Data Index: 2025409 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8675. Min Act: -0.1700
Data Index: 2868635 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8675. Min Act: -0.1700
Data Index: 634615 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8516. Min Act: -0.1700
Data Index: 8815588 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8516. Min Act: -0.1700
Data Index: 6511260 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8516. Min Act: -0.1700
Data Index: 4822046 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8357. Min Act: -0.1700
Data Index: 7564075 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8516. Min Act: -0.1700
Data Index: 3508340 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8198. Min Act: -0.1700
Data Index: 3967715 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8357. Min Act: -0.1700
Data Index: 2579024 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8357. Min Act: -0.1700
Data Index: 4380958 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8357. Min Act: -0.1700
Data Index: 539196 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9151. Min Range: -2.9151
Max Act: 2.8357. Min Act: -0.1700
Data Index: 7252046 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19