Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3047 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.8869. Min Act: -0.1700
Data Index: 7052142 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.6994. Min Act: -0.1700
Data Index: 1185185 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.6369. Min Act: -0.1700
Data Index: 8172715 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.5744. Min Act: -0.1700
Data Index: 3978922 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.5119. Min Act: -0.1700
Data Index: 8029561 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.4494. Min Act: -0.1700
Data Index: 7482580 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.4494. Min Act: -0.1700
Data Index: 5928317 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.4494. Min Act: -0.1700
Data Index: 7301150 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.3869. Min Act: -0.1700
Data Index: 298730 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.2619. Min Act: -0.1700
Data Index: 5473707 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.2619. Min Act: -0.1700
Data Index: 740737 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.2619. Min Act: -0.1700
Data Index: 3246848 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.1994. Min Act: -0.1700
Data Index: 3550370 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.1994. Min Act: -0.1700
Data Index: 5188688 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.1994. Min Act: -0.1700
Data Index: 1375833 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.1994. Min Act: -0.1700
Data Index: 3440760 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.1369. Min Act: -0.1700
Data Index: 1771372 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.1369. Min Act: -0.1700
Data Index: 3484932 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.1369. Min Act: -0.1700
Data Index: 6087118 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8869. Min Range: -9.8869
Max Act: 9.1369. Min Act: -0.1700
Data Index: 7933119 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19