Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5059 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.5716. Min Act: -0.1700
Data Index: 8573851 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.5091. Min Act: -0.1700
Data Index: 6751318 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.3216. Min Act: -0.1700
Data Index: 2507381 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.3216. Min Act: -0.1700
Data Index: 7112327 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2904. Min Act: -0.1700
Data Index: 3311666 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2904. Min Act: -0.1700
Data Index: 6322629 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2904. Min Act: -0.1700
Data Index: 5205263 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2904. Min Act: -0.1700
Data Index: 977712 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2591. Min Act: -0.1700
Data Index: 7310673 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2591. Min Act: -0.1700
Data Index: 8826897 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2591. Min Act: -0.1700
Data Index: 2169883 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2279. Min Act: -0.1700
Data Index: 7501497 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2591. Min Act: -0.1700
Data Index: 474078 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2279. Min Act: -0.1700
Data Index: 3987939 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2279. Min Act: -0.1700
Data Index: 2879690 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2279. Min Act: -0.1700
Data Index: 2091404 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.1966. Min Act: -0.1700
Data Index: 3579140 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.1966. Min Act: -0.1700
Data Index: 5212114 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.2279. Min Act: -0.1700
Data Index: 1207783 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5716. Min Range: -5.5716
Max Act: 5.1654. Min Act: -0.1700
Data Index: 7166216 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #19