Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4000 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.6712. Min Act: -0.1700
Data Index: 1824093 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.6087. Min Act: -0.1700
Data Index: 5136875 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.6087. Min Act: -0.1700
Data Index: 3353217 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.5462. Min Act: -0.1700
Data Index: 1408147 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.5774. Min Act: -0.1700
Data Index: 6245128 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.5462. Min Act: -0.1700
Data Index: 1997969 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.5462. Min Act: -0.1700
Data Index: 809609 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.5149. Min Act: -0.1700
Data Index: 1094269 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.4837. Min Act: -0.1700
Data Index: 933025 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.4837. Min Act: -0.1700
Data Index: 7196711 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.4524. Min Act: -0.1700
Data Index: 6298600 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.4212. Min Act: -0.1700
Data Index: 142696 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.4212. Min Act: -0.1700
Data Index: 4292606 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.3587. Min Act: -0.1700
Data Index: 4132179 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.3587. Min Act: -0.1700
Data Index: 1443040 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.3587. Min Act: -0.1700
Data Index: 3008347 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.3274. Min Act: -0.1700
Data Index: 3449294 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.3274. Min Act: -0.1700
Data Index: 1129079 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.2962. Min Act: -0.1700
Data Index: 5462740 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6712. Min Range: -5.6712
Max Act: 5.2962. Min Act: -0.1700
Data Index: 1094267 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19