Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3848 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.8636. Min Act: -0.1700
Data Index: 5606144 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.8159. Min Act: -0.1700
Data Index: 3199313 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7841. Min Act: -0.1700
Data Index: 2581803 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7522. Min Act: -0.1700
Data Index: 2347076 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7362. Min Act: -0.1700
Data Index: 1820833 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7362. Min Act: -0.1700
Data Index: 2980383 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7362. Min Act: -0.1700
Data Index: 5570516 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7202. Min Act: -0.1700
Data Index: 6335284 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7202. Min Act: -0.1700
Data Index: 3035045 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7202. Min Act: -0.1700
Data Index: 6839043 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7202. Min Act: -0.1700
Data Index: 935773 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7202. Min Act: -0.1700
Data Index: 4857785 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7202. Min Act: -0.1700
Data Index: 5296743 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7202. Min Act: -0.1700
Data Index: 1534362 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7202. Min Act: -0.1700
Data Index: 5473843 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7042. Min Act: -0.1700
Data Index: 5433998 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7042. Min Act: -0.1700
Data Index: 1716678 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7042. Min Act: -0.1700
Data Index: 3425822 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7042. Min Act: -0.1700
Data Index: 1908800 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8636. Min Range: -2.8636
Max Act: 2.7042. Min Act: -0.1700
Data Index: 4271075 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19