Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 78 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4086. Min Range: -6.4086
Max Act: 6.4086. Min Act: -0.1700
Data Index: 8172848 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4086. Min Range: -6.4086
Max Act: 6.3773. Min Act: -0.1700
Data Index: 611286 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4086. Min Range: -6.4086
Max Act: 6.2836. Min Act: -0.1700
Data Index: 7463323 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4086. Min Range: -6.4086
Max Act: 6.2836. Min Act: -0.1700
Data Index: 2439041 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4086. Min Range: -6.4086
Max Act: 6.1898. Min Act: -0.1700
Data Index: 2439042 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4086. Min Range: -6.4086
Max Act: 6.1586. Min Act: -0.1700
Data Index: 6080271 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4086. Min Range: -6.4086
Max Act: 6.0648. Min Act: -0.1700
Data Index: 931400 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4086. Min Range: -6.4086
Max Act: 6.0336. Min Act: -0.1700
Data Index: 523317 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.9711. Min Act: -0.1700
Data Index: 8640250 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.9711. Min Act: -0.1700
Data Index: 2255790 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.9711. Min Act: -0.1700
Data Index: 6487345 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.9398. Min Act: -0.1700
Data Index: 3555294 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.9086. Min Act: -0.1700
Data Index: 5520533 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.8773. Min Act: -0.1700
Data Index: 5202921 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.8773. Min Act: -0.1700
Data Index: 5383252 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.8461. Min Act: -0.1700
Data Index: 7541568 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.8461. Min Act: -0.1700
Data Index: 8647766 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.8461. Min Act: -0.1700
Data Index: 875803 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.8461. Min Act: -0.1700
Data Index: 1582000 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4086. Min Range: -6.4086
Max Act: 5.8148. Min Act: -0.1700
Data Index: 2288882 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19