Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3151 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.7225. Min Act: -0.1700
Data Index: 2993199 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.7065. Min Act: -0.1700
Data Index: 450612 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6745. Min Act: -0.1700
Data Index: 4089686 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.6103. Min Act: -0.1700
Data Index: 7256576 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5942. Min Act: -0.1700
Data Index: 8697775 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5942. Min Act: -0.1700
Data Index: 1084923 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5781. Min Act: -0.1700
Data Index: 123974 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5620. Min Act: -0.1700
Data Index: 3695658 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5620. Min Act: -0.1700
Data Index: 123978 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5781. Min Act: -0.1700
Data Index: 1702120 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5620. Min Act: -0.1700
Data Index: 7012176 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5620. Min Act: -0.1700
Data Index: 6890901 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5620. Min Act: -0.1700
Data Index: 6131332 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5620. Min Act: -0.1700
Data Index: 3626260 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5620. Min Act: -0.1700
Data Index: 3475657 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5620. Min Act: -0.1700
Data Index: 4123847 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5620. Min Act: -0.1700
Data Index: 1702127 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5458. Min Act: -0.1700
Data Index: 6374447 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5458. Min Act: -0.1700
Data Index: 1818029 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7225. Min Range: -2.7225
Max Act: 2.5458. Min Act: -0.1700
Data Index: 306999 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19