Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.4403. Min Act: -0.1700
Data Index: 6330372 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.4091. Min Act: -0.1700
Data Index: 1272660 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.3778. Min Act: -0.1700
Data Index: 7419955 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.3466. Min Act: -0.1700
Data Index: 3146386 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.3153. Min Act: -0.1700
Data Index: 181989 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.2216. Min Act: -0.1700
Data Index: 8772652 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.2216. Min Act: -0.1700
Data Index: 2407260 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.1903. Min Act: -0.1700
Data Index: 8469577 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.1903. Min Act: -0.1700
Data Index: 7368442 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.1591. Min Act: -0.1700
Data Index: 6874112 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.0966. Min Act: -0.1700
Data Index: 1437393 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.0341. Min Act: -0.1700
Data Index: 23283 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.0028. Min Act: -0.1700
Data Index: 3445213 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.0028. Min Act: -0.1700
Data Index: 6526177 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.0028. Min Act: -0.1700
Data Index: 5040496 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4403. Min Range: -6.4403
Max Act: 5.9403. Min Act: -0.1700
Data Index: 6380819 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4403. Min Range: -6.4403
Max Act: 5.9716. Min Act: -0.1700
Data Index: 1434532 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4403. Min Range: -6.4403
Max Act: 5.9716. Min Act: -0.1700
Data Index: 7454655 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4403. Min Range: -6.4403
Max Act: 6.0028. Min Act: -0.1700
Data Index: 4332144 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4403. Min Range: -6.4403
Max Act: 5.9716. Min Act: -0.1700
Data Index: 5824847 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19