Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 841 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5906. Min Act: -0.1700
Data Index: 209189 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.6067. Min Act: -0.1700
Data Index: 1925205 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5906. Min Act: -0.1700
Data Index: 8420170 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.6067. Min Act: -0.1700
Data Index: 3482867 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.6067. Min Act: -0.1700
Data Index: 946062 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.6067. Min Act: -0.1700
Data Index: 6626780 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5906. Min Act: -0.1700
Data Index: 8511122 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5584. Min Act: -0.1700
Data Index: 7548061 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5745. Min Act: -0.1700
Data Index: 6382773 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5584. Min Act: -0.1700
Data Index: 7548053 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5423. Min Act: -0.1700
Data Index: 3858907 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5584. Min Act: -0.1700
Data Index: 4467834 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5261. Min Act: -0.1700
Data Index: 8470414 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5423. Min Act: -0.1700
Data Index: 2740650 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5423. Min Act: -0.1700
Data Index: 1619689 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5261. Min Act: -0.1700
Data Index: 1503076 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5261. Min Act: -0.1700
Data Index: 2754950 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5261. Min Act: -0.1700
Data Index: 7309845 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5261. Min Act: -0.1700
Data Index: 4669492 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6067. Min Range: -2.6067
Max Act: 2.5261. Min Act: -0.1700
Data Index: 1862523 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #19