Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2024. Min Range: -5.2024
Max Act: 5.2024. Min Act: -0.1700
Data Index: 1808078 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2024. Min Range: -5.2024
Max Act: 5.2024. Min Act: -0.1700
Data Index: 5600549 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2024. Min Range: -5.2024
Max Act: 5.1399. Min Act: -0.1700
Data Index: 6909830 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2024. Min Range: -5.2024
Max Act: 5.0149. Min Act: -0.1700
Data Index: 64649 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2024. Min Range: -5.2024
Max Act: 5.0149. Min Act: -0.1700
Data Index: 3091908 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2024. Min Range: -5.2024
Max Act: 5.0149. Min Act: -0.1700
Data Index: 7107334 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2024. Min Range: -5.2024
Max Act: 5.0149. Min Act: -0.1700
Data Index: 6928778 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2024. Min Range: -5.2024
Max Act: 5.0149. Min Act: -0.1700
Data Index: 2602531 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.9524. Min Act: -0.1700
Data Index: 2449218 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2024. Min Range: -5.2024
Max Act: 5.0149. Min Act: -0.1700
Data Index: 2971302 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.9524. Min Act: -0.1700
Data Index: 6075538 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.9524. Min Act: -0.1700
Data Index: 1527633 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.9211. Min Act: -0.1700
Data Index: 3575795 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.8899. Min Act: -0.1700
Data Index: 2366846 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.9211. Min Act: -0.1700
Data Index: 2106410 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.9211. Min Act: -0.1700
Data Index: 4547545 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.9524. Min Act: -0.1700
Data Index: 4355872 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.8586. Min Act: -0.1700
Data Index: 4489645 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.9211. Min Act: -0.1700
Data Index: 4575713 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2024. Min Range: -5.2024
Max Act: 4.8899. Min Act: -0.1700
Data Index: 3001778 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19