Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.2550. Min Act: -0.1700
Data Index: 3393329 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.2550. Min Act: -0.1700
Data Index: 1103869 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.2550. Min Act: -0.1700
Data Index: 2271212 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1925. Min Act: -0.1700
Data Index: 6363299 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.2238. Min Act: -0.1700
Data Index: 5607091 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.2238. Min Act: -0.1700
Data Index: 4712066 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.2238. Min Act: -0.1700
Data Index: 4166137 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1925. Min Act: -0.1700
Data Index: 1476870 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1925. Min Act: -0.1700
Data Index: 4964948 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1613. Min Act: -0.1700
Data Index: 4644749 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1613. Min Act: -0.1700
Data Index: 5117049 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1613. Min Act: -0.1700
Data Index: 891152 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1300. Min Act: -0.1700
Data Index: 6086402 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1300. Min Act: -0.1700
Data Index: 4572458 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1300. Min Act: -0.1700
Data Index: 8487571 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1613. Min Act: -0.1700
Data Index: 6116384 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1300. Min Act: -0.1700
Data Index: 16671 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.1300. Min Act: -0.1700
Data Index: 4122105 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.0988. Min Act: -0.1700
Data Index: 931893 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2550. Min Range: -4.2550
Max Act: 4.0988. Min Act: -0.1700
Data Index: 2086567 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19