Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.5757. Min Act: -0.1700
Data Index: 4015114 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.4194. Min Act: -0.1700
Data Index: 4015102 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.3257. Min Act: -0.1700
Data Index: 5612877 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.2944. Min Act: -0.1700
Data Index: 6833434 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.2632. Min Act: -0.1700
Data Index: 6614895 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.2007. Min Act: -0.1700
Data Index: 7836350 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.1694. Min Act: -0.1700
Data Index: 8301641 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.2007. Min Act: -0.1700
Data Index: 7250136 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.2007. Min Act: -0.1700
Data Index: 3569046 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.1382. Min Act: -0.1700
Data Index: 2808613 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.1069. Min Act: -0.1700
Data Index: 5957407 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.1382. Min Act: -0.1700
Data Index: 8703464 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.1382. Min Act: -0.1700
Data Index: 6108065 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.1382. Min Act: -0.1700
Data Index: 7237227 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.1069. Min Act: -0.1700
Data Index: 1721949 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.1069. Min Act: -0.1700
Data Index: 3272018 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.0757. Min Act: -0.1700
Data Index: 8531952 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.0757. Min Act: -0.1700
Data Index: 2239079 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.0444. Min Act: -0.1700
Data Index: 1718376 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5757. Min Range: -6.5757
Max Act: 6.0444. Min Act: -0.1700
Data Index: 6293660 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19