Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4932 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2524. Min Range: -9.2524
Max Act: 9.2524. Min Act: -0.1700
Data Index: 718318 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2524. Min Range: -9.2524
Max Act: 9.1899. Min Act: -0.1700
Data Index: 6702769 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2524. Min Range: -9.2524
Max Act: 9.1899. Min Act: -0.1700
Data Index: 932430 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2524. Min Range: -9.2524
Max Act: 9.1274. Min Act: -0.1700
Data Index: 5665468 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2524. Min Range: -9.2524
Max Act: 9.0649. Min Act: -0.1700
Data Index: 6702758 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2524. Min Range: -9.2524
Max Act: 9.0024. Min Act: -0.1700
Data Index: 6702750 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2524. Min Range: -9.2524
Max Act: 9.0024. Min Act: -0.1700
Data Index: 6702766 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.9399. Min Act: -0.1700
Data Index: 2536269 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.9399. Min Act: -0.1700
Data Index: 6702752 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.9399. Min Act: -0.1700
Data Index: 785788 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.8774. Min Act: -0.1700
Data Index: 4597370 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.8774. Min Act: -0.1700
Data Index: 5007003 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.7524. Min Act: -0.1700
Data Index: 6702746 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.7524. Min Act: -0.1700
Data Index: 7084730 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.7524. Min Act: -0.1700
Data Index: 5781439 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.8149. Min Act: -0.1700
Data Index: 4765046 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.8149. Min Act: -0.1700
Data Index: 3274853 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.7524. Min Act: -0.1700
Data Index: 2008950 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.6899. Min Act: -0.1700
Data Index: 8739486 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2524. Min Range: -9.2524
Max Act: 8.6274. Min Act: -0.1700
Data Index: 724392 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19