Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 887 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.5893. Min Act: -0.1700
Data Index: 874170 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.4643. Min Act: -0.1700
Data Index: 4653699 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.4643. Min Act: -0.1700
Data Index: 5048152 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.4643. Min Act: -0.1700
Data Index: 5341005 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.4330. Min Act: -0.1700
Data Index: 6380123 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.3080. Min Act: -0.1700
Data Index: 8685854 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.3080. Min Act: -0.1700
Data Index: 2603166 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.3080. Min Act: -0.1700
Data Index: 4595045 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.3080. Min Act: -0.1700
Data Index: 4193317 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.2767. Min Act: -0.1700
Data Index: 2257087 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.2142. Min Act: -0.1700
Data Index: 1538659 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.2455. Min Act: -0.1700
Data Index: 4446993 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.2455. Min Act: -0.1700
Data Index: 3960952 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.2142. Min Act: -0.1700
Data Index: 7154835 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.2142. Min Act: -0.1700
Data Index: 5301228 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.2455. Min Act: -0.1700
Data Index: 3374351 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.1830. Min Act: -0.1700
Data Index: 5053108 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.1830. Min Act: -0.1700
Data Index: 5339153 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.1830. Min Act: -0.1700
Data Index: 1550907 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5893. Min Range: -4.5893
Max Act: 4.1830. Min Act: -0.1700
Data Index: 508480 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19