Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2171 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.4783. Min Act: -0.1700
Data Index: 6666465 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.3220. Min Act: -0.1700
Data Index: 7038834 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.2907. Min Act: -0.1700
Data Index: 6112955 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.1970. Min Act: -0.1700
Data Index: 8341179 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.1345. Min Act: -0.1700
Data Index: 2334291 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.1345. Min Act: -0.1700
Data Index: 5205076 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.1345. Min Act: -0.1700
Data Index: 4993033 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.1657. Min Act: -0.1700
Data Index: 2862447 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.1657. Min Act: -0.1700
Data Index: 3882400 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.1032. Min Act: -0.1700
Data Index: 3892562 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.1032. Min Act: -0.1700
Data Index: 7752864 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.1032. Min Act: -0.1700
Data Index: 1567285 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.1032. Min Act: -0.1700
Data Index: 4536162 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.0407. Min Act: -0.1700
Data Index: 400597 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.0720. Min Act: -0.1700
Data Index: 3556535 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.0720. Min Act: -0.1700
Data Index: 1974832 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.0720. Min Act: -0.1700
Data Index: 4425848 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.0720. Min Act: -0.1700
Data Index: 4761817 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.0407. Min Act: -0.1700
Data Index: 1980934 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4783. Min Range: -4.4783
Max Act: 4.0407. Min Act: -0.1700
Data Index: 2603587 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19