Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2822 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.3845. Min Act: -0.1700
Data Index: 6164970 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.3220. Min Act: -0.1700
Data Index: 3340629 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.2283. Min Act: -0.1700
Data Index: 7912439 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.2283. Min Act: -0.1700
Data Index: 4424541 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.2283. Min Act: -0.1700
Data Index: 4154942 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.2283. Min Act: -0.1700
Data Index: 4628136 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.2283. Min Act: -0.1700
Data Index: 2900670 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1658. Min Act: -0.1700
Data Index: 3934483 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1970. Min Act: -0.1700
Data Index: 4344226 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1970. Min Act: -0.1700
Data Index: 2019461 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1658. Min Act: -0.1700
Data Index: 7004907 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1658. Min Act: -0.1700
Data Index: 2259247 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1658. Min Act: -0.1700
Data Index: 3813673 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1658. Min Act: -0.1700
Data Index: 8362198 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1658. Min Act: -0.1700
Data Index: 6120062 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1658. Min Act: -0.1700
Data Index: 3659098 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1658. Min Act: -0.1700
Data Index: 457160 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1345. Min Act: -0.1700
Data Index: 6184688 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1345. Min Act: -0.1700
Data Index: 3677433 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3845. Min Range: -5.3845
Max Act: 5.1345. Min Act: -0.1700
Data Index: 4347611 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19