Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5304 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1629. Min Range: -12.1629
Max Act: 12.1629. Min Act: -0.1700
Data Index: 6870988 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1629. Min Range: -12.1629
Max Act: 11.9754. Min Act: -0.1700
Data Index: 4048452 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1629. Min Range: -12.1629
Max Act: 11.2879. Min Act: -0.1700
Data Index: 5184929 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1629. Min Range: -12.1629
Max Act: 11.2254. Min Act: -0.1700
Data Index: 395970 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1629. Min Range: -12.1629
Max Act: 11.2254. Min Act: -0.1700
Data Index: 5539185 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1629. Min Range: -12.1629
Max Act: 11.1629. Min Act: -0.1700
Data Index: 2833824 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1629. Min Range: -12.1629
Max Act: 11.0379. Min Act: -0.1700
Data Index: 7560968 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1629. Min Range: -12.1629
Max Act: 11.0379. Min Act: -0.1700
Data Index: 2696364 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1629. Min Range: -12.1629
Max Act: 11.0379. Min Act: -0.1700
Data Index: 1778082 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1629. Min Range: -12.1629
Max Act: 11.0379. Min Act: -0.1700
Data Index: 3674174 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1629. Min Range: -12.1629
Max Act: 10.9754. Min Act: -0.1700
Data Index: 4321758 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1629. Min Range: -12.1629
Max Act: 10.9754. Min Act: -0.1700
Data Index: 4554023 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1629. Min Range: -12.1629
Max Act: 10.8504. Min Act: -0.1700
Data Index: 7125037 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1629. Min Range: -12.1629
Max Act: 10.8504. Min Act: -0.1700
Data Index: 2348210 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1629. Min Range: -12.1629
Max Act: 10.7254. Min Act: -0.1700
Data Index: 3865940 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1629. Min Range: -12.1629
Max Act: 10.7879. Min Act: -0.1700
Data Index: 6376346 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1629. Min Range: -12.1629
Max Act: 10.7879. Min Act: -0.1700
Data Index: 4632440 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1629. Min Range: -12.1629
Max Act: 10.7879. Min Act: -0.1700
Data Index: 558557 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1629. Min Range: -12.1629
Max Act: 10.7879. Min Act: -0.1700
Data Index: 218890 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1629. Min Range: -12.1629
Max Act: 10.7254. Min Act: -0.1700
Data Index: 849369 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19