Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1437 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2973. Min Range: -5.2973
Max Act: 5.2973. Min Act: -0.1700
Data Index: 7341307 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2973. Min Range: -5.2973
Max Act: 5.2660. Min Act: -0.1700
Data Index: 3340320 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2973. Min Range: -5.2973
Max Act: 5.1723. Min Act: -0.1700
Data Index: 2016636 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2973. Min Range: -5.2973
Max Act: 5.0473. Min Act: -0.1700
Data Index: 5724998 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.9535. Min Act: -0.1700
Data Index: 5918232 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.9223. Min Act: -0.1700
Data Index: 2696343 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.9223. Min Act: -0.1700
Data Index: 2296685 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.9223. Min Act: -0.1700
Data Index: 3237361 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.9223. Min Act: -0.1700
Data Index: 2262263 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.8910. Min Act: -0.1700
Data Index: 2439391 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.9223. Min Act: -0.1700
Data Index: 5559796 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.8910. Min Act: -0.1700
Data Index: 6809730 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.8598. Min Act: -0.1700
Data Index: 4497766 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.8598. Min Act: -0.1700
Data Index: 7162077 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.8598. Min Act: -0.1700
Data Index: 1547194 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.7973. Min Act: -0.1700
Data Index: 1299385 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.7973. Min Act: -0.1700
Data Index: 698662 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.7973. Min Act: -0.1700
Data Index: 6365397 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.7660. Min Act: -0.1700
Data Index: 5931049 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2973. Min Range: -5.2973
Max Act: 4.7348. Min Act: -0.1700
Data Index: 4427822 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19