Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5764 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0880. Min Range: -4.0880
Max Act: 4.0880. Min Act: -0.1700
Data Index: 8243307 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0880. Min Range: -4.0880
Max Act: 4.0568. Min Act: -0.1700
Data Index: 6725366 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.9630. Min Act: -0.1700
Data Index: 6848926 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.9317. Min Act: -0.1700
Data Index: 3749607 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8692. Min Act: -0.1700
Data Index: 8543985 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.9005. Min Act: -0.1700
Data Index: 2932096 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8692. Min Act: -0.1700
Data Index: 2448211 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8692. Min Act: -0.1700
Data Index: 6044123 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8692. Min Act: -0.1700
Data Index: 2018304 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8379. Min Act: -0.1700
Data Index: 3951600 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8379. Min Act: -0.1700
Data Index: 5894180 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8379. Min Act: -0.1700
Data Index: 872716 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8379. Min Act: -0.1700
Data Index: 3433161 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8379. Min Act: -0.1700
Data Index: 6785230 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8067. Min Act: -0.1700
Data Index: 3865889 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8067. Min Act: -0.1700
Data Index: 4218392 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8067. Min Act: -0.1700
Data Index: 7080139 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8067. Min Act: -0.1700
Data Index: 7362394 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8067. Min Act: -0.1700
Data Index: 2368020 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0880. Min Range: -4.0880
Max Act: 3.8067. Min Act: -0.1700
Data Index: 5474970 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19