Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2155. Min Range: -4.2155
Max Act: 4.2155. Min Act: -0.1700
Data Index: 3911986 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2155. Min Range: -4.2155
Max Act: 4.1842. Min Act: -0.1700
Data Index: 2409620 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2155. Min Range: -4.2155
Max Act: 4.1217. Min Act: -0.1700
Data Index: 7179828 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2155. Min Range: -4.2155
Max Act: 4.1530. Min Act: -0.1700
Data Index: 304897 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2155. Min Range: -4.2155
Max Act: 4.1530. Min Act: -0.1700
Data Index: 4206042 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2155. Min Range: -4.2155
Max Act: 4.1530. Min Act: -0.1700
Data Index: 4176188 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2155. Min Range: -4.2155
Max Act: 4.0592. Min Act: -0.1700
Data Index: 912392 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2155. Min Range: -4.2155
Max Act: 4.0280. Min Act: -0.1700
Data Index: 6945096 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9967. Min Act: -0.1700
Data Index: 3146620 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9967. Min Act: -0.1700
Data Index: 8788602 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9967. Min Act: -0.1700
Data Index: 3252621 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9654. Min Act: -0.1700
Data Index: 300937 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9654. Min Act: -0.1700
Data Index: 5346847 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9654. Min Act: -0.1700
Data Index: 7374841 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9342. Min Act: -0.1700
Data Index: 7965316 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9342. Min Act: -0.1700
Data Index: 3902644 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9342. Min Act: -0.1700
Data Index: 8148415 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9342. Min Act: -0.1700
Data Index: 1656613 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9342. Min Act: -0.1700
Data Index: 5248289 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2155. Min Range: -4.2155
Max Act: 3.9029. Min Act: -0.1700
Data Index: 4663659 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19