Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5829 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.7083. Min Act: -0.1700
Data Index: 8267988 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.6146. Min Act: -0.1700
Data Index: 4671731 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.6146. Min Act: -0.1700
Data Index: 124360 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.6146. Min Act: -0.1700
Data Index: 4006350 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.5833. Min Act: -0.1700
Data Index: 961510 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.5833. Min Act: -0.1700
Data Index: 7512338 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.5521. Min Act: -0.1700
Data Index: 3205263 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.4896. Min Act: -0.1700
Data Index: 3355534 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.5208. Min Act: -0.1700
Data Index: 527732 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.4583. Min Act: -0.1700
Data Index: 2525241 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.4583. Min Act: -0.1700
Data Index: 7318980 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.4583. Min Act: -0.1700
Data Index: 5340157 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.4271. Min Act: -0.1700
Data Index: 6680111 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.3958. Min Act: -0.1700
Data Index: 7728684 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.3958. Min Act: -0.1700
Data Index: 3386196 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.3958. Min Act: -0.1700
Data Index: 4734510 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.3646. Min Act: -0.1700
Data Index: 3093167 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.3333. Min Act: -0.1700
Data Index: 3125806 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.3021. Min Act: -0.1700
Data Index: 5096529 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7083. Min Range: -7.7083
Max Act: 7.2708. Min Act: -0.1700
Data Index: 6052669 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19