Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4185 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0597. Min Range: -7.0597
Max Act: 7.0597. Min Act: -0.1700
Data Index: 1607900 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.9972. Min Act: -0.1700
Data Index: 1673140 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.9660. Min Act: -0.1700
Data Index: 4146263 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.8410. Min Act: -0.1700
Data Index: 2896984 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.8097. Min Act: -0.1700
Data Index: 193450 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.7785. Min Act: -0.1700
Data Index: 3006109 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.7472. Min Act: -0.1700
Data Index: 5662400 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.7160. Min Act: -0.1700
Data Index: 5048651 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.6847. Min Act: -0.1700
Data Index: 753437 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.6847. Min Act: -0.1700
Data Index: 3586049 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.6222. Min Act: -0.1700
Data Index: 6370645 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.6535. Min Act: -0.1700
Data Index: 7967013 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.6535. Min Act: -0.1700
Data Index: 5323421 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.5910. Min Act: -0.1700
Data Index: 128387 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.5910. Min Act: -0.1700
Data Index: 4320114 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.5910. Min Act: -0.1700
Data Index: 1499343 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.5597. Min Act: -0.1700
Data Index: 2258892 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.5597. Min Act: -0.1700
Data Index: 6131627 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.5285. Min Act: -0.1700
Data Index: 6692303 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0597. Min Range: -7.0597
Max Act: 6.5910. Min Act: -0.1700
Data Index: 313094 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19