Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6370 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.5992. Min Act: -0.1700
Data Index: 7807058 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.3804. Min Act: -0.1700
Data Index: 8784769 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.2241. Min Act: -0.1700
Data Index: 966140 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.0679. Min Act: -0.1700
Data Index: 46349 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.0991. Min Act: -0.1700
Data Index: 5085949 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.0366. Min Act: -0.1700
Data Index: 1011845 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.0366. Min Act: -0.1700
Data Index: 7037633 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5992. Min Range: -4.5992
Max Act: 4.0053. Min Act: -0.1700
Data Index: 1690965 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.9428. Min Act: -0.1700
Data Index: 6205048 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.9741. Min Act: -0.1700
Data Index: 8487130 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.9115. Min Act: -0.1700
Data Index: 8405843 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.9115. Min Act: -0.1700
Data Index: 2962366 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.9115. Min Act: -0.1700
Data Index: 5093257 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.9115. Min Act: -0.1700
Data Index: 6352511 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.9115. Min Act: -0.1700
Data Index: 71332 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.8803. Min Act: -0.1700
Data Index: 3195784 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.8646. Min Act: -0.1700
Data Index: 7185991 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.8334. Min Act: -0.1700
Data Index: 4076789 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.8334. Min Act: -0.1700
Data Index: 8165449 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5992. Min Range: -4.5992
Max Act: 3.8177. Min Act: -0.1700
Data Index: 4246309 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19