Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2876 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6320. Min Range: -5.6320
Max Act: 5.6320. Min Act: -0.1700
Data Index: 2248959 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6320. Min Range: -5.6320
Max Act: 5.4132. Min Act: -0.1700
Data Index: 4301799 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6320. Min Range: -5.6320
Max Act: 5.4132. Min Act: -0.1700
Data Index: 1733732 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6320. Min Range: -5.6320
Max Act: 5.0695. Min Act: -0.1700
Data Index: 2087240 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6320. Min Range: -5.6320
Max Act: 5.1007. Min Act: -0.1700
Data Index: 1907127 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6320. Min Range: -5.6320
Max Act: 5.0382. Min Act: -0.1700
Data Index: 3150114 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.9445. Min Act: -0.1700
Data Index: 2390371 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.9445. Min Act: -0.1700
Data Index: 3785053 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.9445. Min Act: -0.1700
Data Index: 6715326 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.9132. Min Act: -0.1700
Data Index: 1443051 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.9132. Min Act: -0.1700
Data Index: 1919929 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.9132. Min Act: -0.1700
Data Index: 3144922 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.9132. Min Act: -0.1700
Data Index: 6212217 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.9132. Min Act: -0.1700
Data Index: 3472601 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.9132. Min Act: -0.1700
Data Index: 7491115 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.8820. Min Act: -0.1700
Data Index: 8717063 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.8820. Min Act: -0.1700
Data Index: 8564739 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.8820. Min Act: -0.1700
Data Index: 4411505 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.8820. Min Act: -0.1700
Data Index: 6102022 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6320. Min Range: -5.6320
Max Act: 4.8507. Min Act: -0.1700
Data Index: 1251055 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19