Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 460 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.3730. Min Act: -0.1700
Data Index: 4187387 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.2480. Min Act: -0.1700
Data Index: 3783448 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.1543. Min Act: -0.1700
Data Index: 3220249 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.1855. Min Act: -0.1700
Data Index: 6534906 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.1230. Min Act: -0.1700
Data Index: 8366305 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.1230. Min Act: -0.1700
Data Index: 8366312 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.0605. Min Act: -0.1700
Data Index: 1128369 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.0605. Min Act: -0.1700
Data Index: 2127941 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.0605. Min Act: -0.1700
Data Index: 6047533 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.0605. Min Act: -0.1700
Data Index: 7902460 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.0293. Min Act: -0.1700
Data Index: 7537366 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.0605. Min Act: -0.1700
Data Index: 2013315 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.0605. Min Act: -0.1700
Data Index: 5319062 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.0605. Min Act: -0.1700
Data Index: 7239180 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3730. Min Range: -6.3730
Max Act: 6.0293. Min Act: -0.1700
Data Index: 5050391 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3730. Min Range: -6.3730
Max Act: 5.9980. Min Act: -0.1700
Data Index: 881493 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3730. Min Range: -6.3730
Max Act: 5.9668. Min Act: -0.1700
Data Index: 883721 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3730. Min Range: -6.3730
Max Act: 5.9980. Min Act: -0.1700
Data Index: 5067796 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3730. Min Range: -6.3730
Max Act: 5.9980. Min Act: -0.1700
Data Index: 2935406 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3730. Min Range: -6.3730
Max Act: 5.9668. Min Act: -0.1700
Data Index: 6165613 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19