Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.4817. Min Act: -0.1700
Data Index: 6818004 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.4504. Min Act: -0.1700
Data Index: 4753327 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.3567. Min Act: -0.1700
Data Index: 3653748 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.3879. Min Act: -0.1700
Data Index: 4432426 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.3254. Min Act: -0.1700
Data Index: 7615059 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.3567. Min Act: -0.1700
Data Index: 2760639 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.3567. Min Act: -0.1700
Data Index: 8538908 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.3254. Min Act: -0.1700
Data Index: 5326749 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.3254. Min Act: -0.1700
Data Index: 1344785 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2942. Min Act: -0.1700
Data Index: 8246205 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2942. Min Act: -0.1700
Data Index: 3459740 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2942. Min Act: -0.1700
Data Index: 3242700 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2629. Min Act: -0.1700
Data Index: 4814756 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2629. Min Act: -0.1700
Data Index: 3369264 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2629. Min Act: -0.1700
Data Index: 5836370 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2629. Min Act: -0.1700
Data Index: 743059 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2317. Min Act: -0.1700
Data Index: 6890230 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2317. Min Act: -0.1700
Data Index: 5386458 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2317. Min Act: -0.1700
Data Index: 6902710 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4817. Min Range: -5.4817
Max Act: 5.2004. Min Act: -0.1700
Data Index: 747530 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19