Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 410 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.4716. Min Act: -0.1700
Data Index: 2740120 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.3466. Min Act: -0.1700
Data Index: 784839 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.3466. Min Act: -0.1700
Data Index: 2533009 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.2528. Min Act: -0.1700
Data Index: 7611053 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.2216. Min Act: -0.1700
Data Index: 696752 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.1903. Min Act: -0.1700
Data Index: 5090770 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.2216. Min Act: -0.1700
Data Index: 7691634 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.1903. Min Act: -0.1700
Data Index: 3134199 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.1903. Min Act: -0.1700
Data Index: 934590 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.1591. Min Act: -0.1700
Data Index: 3510537 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.1591. Min Act: -0.1700
Data Index: 7120174 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.1591. Min Act: -0.1700
Data Index: 4546251 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.1591. Min Act: -0.1700
Data Index: 6503884 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.1278. Min Act: -0.1700
Data Index: 8292485 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.1591. Min Act: -0.1700
Data Index: 3813495 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.0966. Min Act: -0.1700
Data Index: 2249087 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.0966. Min Act: -0.1700
Data Index: 8603406 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.1278. Min Act: -0.1700
Data Index: 4626702 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.0966. Min Act: -0.1700
Data Index: 3802582 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4716. Min Range: -5.4716
Max Act: 5.0966. Min Act: -0.1700
Data Index: 772884 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19