Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1488. Min Range: -3.1488
Max Act: 3.1488. Min Act: -0.1700
Data Index: 219181 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1488. Min Range: -3.1488
Max Act: 3.1016. Min Act: -0.1700
Data Index: 3221831 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1488. Min Range: -3.1488
Max Act: 3.1016. Min Act: -0.1700
Data Index: 7689839 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1488. Min Range: -3.1488
Max Act: 3.1173. Min Act: -0.1700
Data Index: 5179285 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1488. Min Range: -3.1488
Max Act: 3.0700. Min Act: -0.1700
Data Index: 2886320 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1488. Min Range: -3.1488
Max Act: 3.0700. Min Act: -0.1700
Data Index: 2025829 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1488. Min Range: -3.1488
Max Act: 3.0700. Min Act: -0.1700
Data Index: 2594763 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1488. Min Range: -3.1488
Max Act: 3.0543. Min Act: -0.1700
Data Index: 3368901 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1488. Min Range: -3.1488
Max Act: 3.0385. Min Act: -0.1700
Data Index: 472726 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9911. Min Act: -0.1700
Data Index: 1311678 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9911. Min Act: -0.1700
Data Index: 6831701 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9595. Min Act: -0.1700
Data Index: 2037953 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9595. Min Act: -0.1700
Data Index: 3678723 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9595. Min Act: -0.1700
Data Index: 8510798 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9753. Min Act: -0.1700
Data Index: 5283768 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9753. Min Act: -0.1700
Data Index: 4509772 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9753. Min Act: -0.1700
Data Index: 1574973 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9753. Min Act: -0.1700
Data Index: 6446919 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9595. Min Act: -0.1700
Data Index: 2496048 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1488. Min Range: -3.1488
Max Act: 2.9436. Min Act: -0.1700
Data Index: 4441504 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19