Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2761 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.6607. Min Act: -0.1700
Data Index: 5876514 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.6294. Min Act: -0.1700
Data Index: 3359307 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.5982. Min Act: -0.1700
Data Index: 3359306 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.5669. Min Act: -0.1700
Data Index: 3359290 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.5357. Min Act: -0.1700
Data Index: 1190624 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.5357. Min Act: -0.1700
Data Index: 3359313 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.4732. Min Act: -0.1700
Data Index: 5757159 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.4419. Min Act: -0.1700
Data Index: 3359303 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.4107. Min Act: -0.1700
Data Index: 824740 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.4107. Min Act: -0.1700
Data Index: 3255195 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.3482. Min Act: -0.1700
Data Index: 318938 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.3482. Min Act: -0.1700
Data Index: 2662960 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.3169. Min Act: -0.1700
Data Index: 3359300 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.3482. Min Act: -0.1700
Data Index: 6074563 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.3169. Min Act: -0.1700
Data Index: 3359293 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.3482. Min Act: -0.1700
Data Index: 7973896 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.3169. Min Act: -0.1700
Data Index: 1423184 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.3169. Min Act: -0.1700
Data Index: 3359299 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.3169. Min Act: -0.1700
Data Index: 4049733 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6607. Min Range: -6.6607
Max Act: 6.3169. Min Act: -0.1700
Data Index: 6177046 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19