Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3996 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.6171. Min Act: -0.1700
Data Index: 6498879 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.6796. Min Act: -0.1700
Data Index: 2858702 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.5234. Min Act: -0.1700
Data Index: 8712067 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.3984. Min Act: -0.1700
Data Index: 4654045 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.3671. Min Act: -0.1700
Data Index: 4120302 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.3984. Min Act: -0.1700
Data Index: 1451201 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.3984. Min Act: -0.1700
Data Index: 2629007 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.3359. Min Act: -0.1700
Data Index: 720598 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.3359. Min Act: -0.1700
Data Index: 6368220 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.3046. Min Act: -0.1700
Data Index: 150663 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.3359. Min Act: -0.1700
Data Index: 2382231 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.2734. Min Act: -0.1700
Data Index: 7653422 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.2421. Min Act: -0.1700
Data Index: 145927 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.2734. Min Act: -0.1700
Data Index: 4023735 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.1796. Min Act: -0.1700
Data Index: 1839752 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.1484. Min Act: -0.1700
Data Index: 7907728 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.0859. Min Act: -0.1700
Data Index: 7541414 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.0546. Min Act: -0.1700
Data Index: 1943325 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.0859. Min Act: -0.1700
Data Index: 4689390 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6796. Min Range: -5.6796
Max Act: 5.0546. Min Act: -0.1700
Data Index: 4312610 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #19