Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3069 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7509. Min Act: -0.1700
Data Index: 3998042 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.7509. Min Act: -0.1700
Data Index: 185042 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6883. Min Act: -0.1700
Data Index: 7086008 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6883. Min Act: -0.1700
Data Index: 7391146 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6414. Min Act: -0.1700
Data Index: 3567780 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6257. Min Act: -0.1700
Data Index: 1918481 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6414. Min Act: -0.1700
Data Index: 619960 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.6257. Min Act: -0.1700
Data Index: 2176366 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5788. Min Act: -0.1700
Data Index: 1819378 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5944. Min Act: -0.1700
Data Index: 6646261 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5944. Min Act: -0.1700
Data Index: 451140 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5944. Min Act: -0.1700
Data Index: 7398116 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5631. Min Act: -0.1700
Data Index: 2038238 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5788. Min Act: -0.1700
Data Index: 8435713 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5788. Min Act: -0.1700
Data Index: 1791513 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5475. Min Act: -0.1700
Data Index: 2622399 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5788. Min Act: -0.1700
Data Index: 5741373 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5631. Min Act: -0.1700
Data Index: 340365 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5475. Min Act: -0.1700
Data Index: 7706680 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7509. Min Range: -3.7509
Max Act: 3.5475. Min Act: -0.1700
Data Index: 8653718 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19