Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5596 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.4902. Min Act: -0.1700
Data Index: 5077926 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.4590. Min Act: -0.1700
Data Index: 3604820 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.3652. Min Act: -0.1700
Data Index: 804618 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.3027. Min Act: -0.1700
Data Index: 5459663 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.3027. Min Act: -0.1700
Data Index: 3456621 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.2715. Min Act: -0.1700
Data Index: 1103666 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.2402. Min Act: -0.1700
Data Index: 743008 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.1777. Min Act: -0.1700
Data Index: 856873 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.0840. Min Act: -0.1700
Data Index: 7660163 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.0840. Min Act: -0.1700
Data Index: 5786771 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.0527. Min Act: -0.1700
Data Index: 8354744 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.0215. Min Act: -0.1700
Data Index: 8476863 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4902. Min Range: -6.4902
Max Act: 6.0527. Min Act: -0.1700
Data Index: 6802736 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4902. Min Range: -6.4902
Max Act: 5.9902. Min Act: -0.1700
Data Index: 4275859 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4902. Min Range: -6.4902
Max Act: 5.9590. Min Act: -0.1700
Data Index: 220698 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4902. Min Range: -6.4902
Max Act: 5.9590. Min Act: -0.1700
Data Index: 4288277 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4902. Min Range: -6.4902
Max Act: 5.9590. Min Act: -0.1700
Data Index: 6527217 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4902. Min Range: -6.4902
Max Act: 5.8965. Min Act: -0.1700
Data Index: 5722488 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4902. Min Range: -6.4902
Max Act: 5.8965. Min Act: -0.1700
Data Index: 3532286 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4902. Min Range: -6.4902
Max Act: 5.8965. Min Act: -0.1700
Data Index: 4004160 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19