Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1227. Min Range: -7.1227
Max Act: 7.1227. Min Act: -0.1700
Data Index: 6216412 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1227. Min Range: -7.1227
Max Act: 7.0290. Min Act: -0.1700
Data Index: 4119532 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.9665. Min Act: -0.1700
Data Index: 2946940 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.9352. Min Act: -0.1700
Data Index: 4525693 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.8727. Min Act: -0.1700
Data Index: 7604660 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.8727. Min Act: -0.1700
Data Index: 4968467 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.7790. Min Act: -0.1700
Data Index: 7725487 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.7477. Min Act: -0.1700
Data Index: 7446745 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.7477. Min Act: -0.1700
Data Index: 4181075 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.7477. Min Act: -0.1700
Data Index: 4304180 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.6540. Min Act: -0.1700
Data Index: 981208 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.6852. Min Act: -0.1700
Data Index: 3881694 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.6540. Min Act: -0.1700
Data Index: 8186460 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.6227. Min Act: -0.1700
Data Index: 6608612 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.5915. Min Act: -0.1700
Data Index: 1898013 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.6227. Min Act: -0.1700
Data Index: 4664531 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.6227. Min Act: -0.1700
Data Index: 7710989 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.6540. Min Act: -0.1700
Data Index: 6597956 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.5915. Min Act: -0.1700
Data Index: 4993603 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1227. Min Range: -7.1227
Max Act: 6.5915. Min Act: -0.1700
Data Index: 2660895 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19