Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3178 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0111. Min Range: -5.0111
Max Act: 5.0111. Min Act: -0.1700
Data Index: 7366704 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.9486. Min Act: -0.1700
Data Index: 6123420 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.9174. Min Act: -0.1700
Data Index: 867586 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.8549. Min Act: -0.1700
Data Index: 2001393 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.6361. Min Act: -0.1700
Data Index: 4390249 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.6361. Min Act: -0.1700
Data Index: 6698214 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.5736. Min Act: -0.1700
Data Index: 8168538 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.6049. Min Act: -0.1700
Data Index: 474065 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.5736. Min Act: -0.1700
Data Index: 1631512 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.5736. Min Act: -0.1700
Data Index: 5626087 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.5424. Min Act: -0.1700
Data Index: 2001391 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.5111. Min Act: -0.1699
Data Index: 2207085 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.5111. Min Act: -0.1700
Data Index: 7922461 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.5111. Min Act: -0.1693
Data Index: 6123419 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.5111. Min Act: -0.1700
Data Index: 2089669 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.5111. Min Act: -0.1700
Data Index: 1733183 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.4799. Min Act: -0.1700
Data Index: 684677 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.4799. Min Act: -0.1700
Data Index: 2703352 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.4799. Min Act: -0.1700
Data Index: 6496966 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0111. Min Range: -5.0111
Max Act: 4.4799. Min Act: -0.1700
Data Index: 805662 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #19