Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4184 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0763. Min Range: -8.0763
Max Act: 8.0763. Min Act: -0.1700
Data Index: 687950 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0763. Min Range: -8.0763
Max Act: 8.0138. Min Act: -0.1700
Data Index: 597705 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.7013. Min Act: -0.1700
Data Index: 551385 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.6388. Min Act: -0.1700
Data Index: 3378616 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.6700. Min Act: -0.1700
Data Index: 2055263 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.7013. Min Act: -0.1700
Data Index: 8762493 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.6700. Min Act: -0.1700
Data Index: 5021891 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.6700. Min Act: -0.1700
Data Index: 5725871 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.6388. Min Act: -0.1700
Data Index: 4070583 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.6075. Min Act: -0.1700
Data Index: 7798015 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.6075. Min Act: -0.1700
Data Index: 1433903 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.5763. Min Act: -0.1700
Data Index: 2186556 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.5450. Min Act: -0.1700
Data Index: 3351232 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.5763. Min Act: -0.1700
Data Index: 6166844 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.5450. Min Act: -0.1700
Data Index: 1870803 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.5763. Min Act: -0.1700
Data Index: 4693797 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.5138. Min Act: -0.1700
Data Index: 7037915 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.5450. Min Act: -0.1700
Data Index: 3951598 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.4825. Min Act: -0.1700
Data Index: 7305808 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0763. Min Range: -8.0763
Max Act: 7.4825. Min Act: -0.1700
Data Index: 3275682 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19