Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1028 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.4931. Min Act: -0.1700
Data Index: 1345518 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.3368. Min Act: -0.1700
Data Index: 8158020 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.3368. Min Act: -0.1700
Data Index: 7203671 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.2118. Min Act: -0.1700
Data Index: 6079730 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.2118. Min Act: -0.1700
Data Index: 6020740 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.1493. Min Act: -0.1700
Data Index: 6241772 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.1180. Min Act: -0.1700
Data Index: 5757019 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.0868. Min Act: -0.1700
Data Index: 1788967 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4931. Min Range: -4.4931
Max Act: 4.0243. Min Act: -0.1700
Data Index: 4044596 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9930. Min Act: -0.1700
Data Index: 4843889 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9930. Min Act: -0.1700
Data Index: 2099096 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9617. Min Act: -0.1700
Data Index: 3317329 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9617. Min Act: -0.1700
Data Index: 8539786 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9305. Min Act: -0.1700
Data Index: 6559196 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9617. Min Act: -0.1700
Data Index: 8581726 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9305. Min Act: -0.1700
Data Index: 3777049 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9305. Min Act: -0.1700
Data Index: 5215709 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.9305. Min Act: -0.1700
Data Index: 2391590 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.8992. Min Act: -0.1700
Data Index: 3118172 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4931. Min Range: -4.4931
Max Act: 3.8992. Min Act: -0.1700
Data Index: 3030798 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19