Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1729 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.3535. Min Act: -0.1700
Data Index: 2284151 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.3223. Min Act: -0.1700
Data Index: 6405066 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.1973. Min Act: -0.1700
Data Index: 5318189 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.1973. Min Act: -0.1700
Data Index: 8213218 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.1660. Min Act: -0.1700
Data Index: 5431353 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.1348. Min Act: -0.1700
Data Index: 5652614 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.1660. Min Act: -0.1700
Data Index: 3047064 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.1348. Min Act: -0.1700
Data Index: 2208586 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.0722. Min Act: -0.1700
Data Index: 3536141 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.0722. Min Act: -0.1700
Data Index: 575225 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.0410. Min Act: -0.1700
Data Index: 8828308 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.0410. Min Act: -0.1700
Data Index: 3032176 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.0410. Min Act: -0.1700
Data Index: 4253320 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.0410. Min Act: -0.1700
Data Index: 7672505 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.0097. Min Act: -0.1700
Data Index: 7164413 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.0097. Min Act: -0.1700
Data Index: 2355322 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3535. Min Range: -4.3535
Max Act: 4.0097. Min Act: -0.1700
Data Index: 535453 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3535. Min Range: -4.3535
Max Act: 3.9785. Min Act: -0.1700
Data Index: 1123095 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3535. Min Range: -4.3535
Max Act: 3.9472. Min Act: -0.1700
Data Index: 6704939 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3535. Min Range: -4.3535
Max Act: 3.9472. Min Act: -0.1700
Data Index: 1291170 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19