Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4096 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.7607. Min Act: -0.1700
Data Index: 876662 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.7607. Min Act: -0.1700
Data Index: 5198065 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.6982. Min Act: -0.1700
Data Index: 4933936 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.6669. Min Act: -0.1700
Data Index: 3689701 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.6357. Min Act: -0.1700
Data Index: 4022763 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.6357. Min Act: -0.1700
Data Index: 5541916 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5732. Min Act: -0.1700
Data Index: 2818530 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5732. Min Act: -0.1700
Data Index: 5224794 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5419. Min Act: -0.1700
Data Index: 3398678 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5732. Min Act: -0.1700
Data Index: 2854989 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5732. Min Act: -0.1700
Data Index: 7403074 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5419. Min Act: -0.1700
Data Index: 197452 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5419. Min Act: -0.1700
Data Index: 1242875 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5732. Min Act: -0.1700
Data Index: 879484 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5419. Min Act: -0.1700
Data Index: 2542422 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5419. Min Act: -0.1700
Data Index: 5400342 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5419. Min Act: -0.1700
Data Index: 719876 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.5107. Min Act: -0.1700
Data Index: 2826320 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.4794. Min Act: -0.1700
Data Index: 2327332 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7607. Min Range: -5.7607
Max Act: 5.4794. Min Act: -0.1700
Data Index: 3065925 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19