Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4644 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.8297. Min Act: -0.1700
Data Index: 8122038 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.6109. Min Act: -0.1700
Data Index: 5783326 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.4547. Min Act: -0.1700
Data Index: 7967228 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.3922. Min Act: -0.1700
Data Index: 482230 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.2672. Min Act: -0.1700
Data Index: 6254999 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.2047. Min Act: -0.1700
Data Index: 5516758 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.2047. Min Act: -0.1700
Data Index: 943095 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.1734. Min Act: -0.1700
Data Index: 1744546 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.1422. Min Act: -0.1700
Data Index: 2981841 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.1422. Min Act: -0.1700
Data Index: 5017328 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.1109. Min Act: -0.1700
Data Index: 2538392 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.1109. Min Act: -0.1700
Data Index: 6475450 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.1109. Min Act: -0.1700
Data Index: 7346846 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.1109. Min Act: -0.1700
Data Index: 2066699 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.0484. Min Act: -0.1700
Data Index: 8750633 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.0796. Min Act: -0.1700
Data Index: 8111430 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.0796. Min Act: -0.1700
Data Index: 7721706 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.0796. Min Act: -0.1700
Data Index: 4037759 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.0796. Min Act: -0.1700
Data Index: 607321 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8297. Min Range: -4.8297
Max Act: 4.0171. Min Act: -0.1700
Data Index: 3959412 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19