Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3420. Min Range: -7.3420
Max Act: 7.3420. Min Act: -0.1700
Data Index: 6490556 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3420. Min Range: -7.3420
Max Act: 7.1545. Min Act: -0.1700
Data Index: 1567441 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3420. Min Range: -7.3420
Max Act: 7.0920. Min Act: -0.1700
Data Index: 6108178 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3420. Min Range: -7.3420
Max Act: 7.0607. Min Act: -0.1700
Data Index: 2034101 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3420. Min Range: -7.3420
Max Act: 7.0295. Min Act: -0.1700
Data Index: 903468 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3420. Min Range: -7.3420
Max Act: 7.0295. Min Act: -0.1700
Data Index: 4760434 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.9982. Min Act: -0.1700
Data Index: 4470671 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.9982. Min Act: -0.1700
Data Index: 4060151 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.9982. Min Act: -0.1700
Data Index: 4497075 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.9357. Min Act: -0.1700
Data Index: 6050196 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.9357. Min Act: -0.1700
Data Index: 6074881 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.9357. Min Act: -0.1700
Data Index: 1484696 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.9045. Min Act: -0.1700
Data Index: 38958 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.8732. Min Act: -0.1700
Data Index: 4735573 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.8420. Min Act: -0.1700
Data Index: 558861 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.8420. Min Act: -0.1700
Data Index: 665520 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.8107. Min Act: -0.1700
Data Index: 5421768 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.7795. Min Act: -0.1700
Data Index: 8533105 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.7795. Min Act: -0.1700
Data Index: 4501647 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3420. Min Range: -7.3420
Max Act: 6.7795. Min Act: -0.1700
Data Index: 3892598 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #19