Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2086 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2079. Min Range: -7.2079
Max Act: 7.2079. Min Act: -0.1700
Data Index: 146913 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2079. Min Range: -7.2079
Max Act: 7.0829. Min Act: -0.1700
Data Index: 3829387 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2079. Min Range: -7.2079
Max Act: 7.0204. Min Act: -0.1700
Data Index: 3522482 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.9579. Min Act: -0.1700
Data Index: 7355733 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.8641. Min Act: -0.1700
Data Index: 4027901 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.8641. Min Act: -0.1700
Data Index: 6587117 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.8329. Min Act: -0.1700
Data Index: 4858131 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.8016. Min Act: -0.1700
Data Index: 3893484 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.8016. Min Act: -0.1700
Data Index: 1036868 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.7704. Min Act: -0.1700
Data Index: 1922767 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.8016. Min Act: -0.1700
Data Index: 7270554 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.7704. Min Act: -0.1700
Data Index: 4571042 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.7391. Min Act: -0.1700
Data Index: 2712406 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.6766. Min Act: -0.1700
Data Index: 3825777 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.7079. Min Act: -0.1700
Data Index: 7187970 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.7079. Min Act: -0.1700
Data Index: 6689433 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.6766. Min Act: -0.1700
Data Index: 5914229 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.7079. Min Act: -0.1700
Data Index: 7511248 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.5829. Min Act: -0.1700
Data Index: 4654941 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2079. Min Range: -7.2079
Max Act: 6.5829. Min Act: -0.1700
Data Index: 321206 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19