Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6276 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.8345. Min Act: -0.1700
Data Index: 2235865 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.6311. Min Act: -0.1700
Data Index: 4740623 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.6311. Min Act: -0.1700
Data Index: 5447210 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5842. Min Act: -0.1700
Data Index: 242759 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5529. Min Act: -0.1700
Data Index: 6529728 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5529. Min Act: -0.1700
Data Index: 1015837 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5372. Min Act: -0.1700
Data Index: 4547001 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5529. Min Act: -0.1700
Data Index: 4870790 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5372. Min Act: -0.1700
Data Index: 7540645 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5216. Min Act: -0.1700
Data Index: 5867203 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5372. Min Act: -0.1700
Data Index: 6033759 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5216. Min Act: -0.1700
Data Index: 701974 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5372. Min Act: -0.1700
Data Index: 5425025 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.5216. Min Act: -0.1700
Data Index: 8804767 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.4902. Min Act: -0.1700
Data Index: 2798574 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.4746. Min Act: -0.1700
Data Index: 4510620 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.4902. Min Act: -0.1700
Data Index: 3442516 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.4902. Min Act: -0.1700
Data Index: 6203159 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.4746. Min Act: -0.1700
Data Index: 5591914 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8345. Min Range: -3.8345
Max Act: 3.4746. Min Act: -0.1700
Data Index: 3707367 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19