Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1149 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.3883. Min Act: -0.1700
Data Index: 4839025 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.3883. Min Act: -0.1700
Data Index: 8138615 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.3571. Min Act: -0.1700
Data Index: 7991867 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.2946. Min Act: -0.1700
Data Index: 3878042 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.2946. Min Act: -0.1700
Data Index: 6137131 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.2321. Min Act: -0.1700
Data Index: 1635802 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.2008. Min Act: -0.1700
Data Index: 8512731 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.2321. Min Act: -0.1700
Data Index: 7033454 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.1696. Min Act: -0.1700
Data Index: 4183032 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.1383. Min Act: -0.1700
Data Index: 5866195 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.1383. Min Act: -0.1700
Data Index: 7129819 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.1071. Min Act: -0.1700
Data Index: 4424216 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.1071. Min Act: -0.1700
Data Index: 6291238 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.1071. Min Act: -0.1700
Data Index: 446046 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.1071. Min Act: -0.1700
Data Index: 6980306 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.0758. Min Act: -0.1700
Data Index: 6325722 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.0758. Min Act: -0.1700
Data Index: 5419985 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.0758. Min Act: -0.1700
Data Index: 2635032 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.0446. Min Act: -0.1700
Data Index: 6286548 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3883. Min Range: -7.3883
Max Act: 7.0446. Min Act: -0.1700
Data Index: 7681985 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19