Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2436 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0349. Min Range: -4.0349
Max Act: 4.0349. Min Act: -0.1700
Data Index: 7489569 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0349. Min Range: -4.0349
Max Act: 4.0037. Min Act: -0.1700
Data Index: 176573 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.9724. Min Act: -0.1700
Data Index: 2233662 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.9412. Min Act: -0.1700
Data Index: 2508196 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.9412. Min Act: -0.1700
Data Index: 1905963 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.8786. Min Act: -0.1700
Data Index: 4749754 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.8474. Min Act: -0.1700
Data Index: 2570421 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.8474. Min Act: -0.1700
Data Index: 1397641 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.8161. Min Act: -0.1700
Data Index: 5605612 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.7848. Min Act: -0.1700
Data Index: 2216163 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.7848. Min Act: -0.1700
Data Index: 5562794 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.7848. Min Act: -0.1700
Data Index: 283362 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.7535. Min Act: -0.1700
Data Index: 8386155 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.7535. Min Act: -0.1700
Data Index: 5489953 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.7223. Min Act: -0.1700
Data Index: 6264880 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.7223. Min Act: -0.1700
Data Index: 8433900 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.7223. Min Act: -0.1700
Data Index: 8475310 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.7223. Min Act: -0.1700
Data Index: 6010614 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.7223. Min Act: -0.1700
Data Index: 5947897 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0349. Min Range: -4.0349
Max Act: 3.6910. Min Act: -0.1700
Data Index: 3284086 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19