Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3877 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3973. Min Act: -0.1700
Data Index: 5174330 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3661. Min Act: -0.1700
Data Index: 3501261 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3348. Min Act: -0.1700
Data Index: 8750469 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3348. Min Act: -0.1700
Data Index: 4904436 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3348. Min Act: -0.1700
Data Index: 4495953 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3035. Min Act: -0.1700
Data Index: 1471725 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3035. Min Act: -0.1700
Data Index: 6090083 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3035. Min Act: -0.1700
Data Index: 7792243 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3035. Min Act: -0.1700
Data Index: 6956317 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3035. Min Act: -0.1700
Data Index: 4162131 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3035. Min Act: -0.1700
Data Index: 1595557 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.2723. Min Act: -0.1700
Data Index: 2653245 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3035. Min Act: -0.1700
Data Index: 2519332 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.3035. Min Act: -0.1700
Data Index: 6341121 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.2723. Min Act: -0.1700
Data Index: 3223887 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.2723. Min Act: -0.1700
Data Index: 6855558 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.2723. Min Act: -0.1700
Data Index: 1344983 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.2723. Min Act: -0.1700
Data Index: 6714005 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.2410. Min Act: -0.1700
Data Index: 2229575 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3973. Min Range: -4.3973
Max Act: 4.2410. Min Act: -0.1700
Data Index: 628169 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #19