Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4766 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0111. Min Range: -8.0111
Max Act: 8.0111. Min Act: -0.1700
Data Index: 6671949 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.8236. Min Act: -0.1700
Data Index: 1645793 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.7611. Min Act: -0.1700
Data Index: 7382482 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.6674. Min Act: -0.1700
Data Index: 5226935 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.6674. Min Act: -0.1700
Data Index: 8104692 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.6049. Min Act: -0.1700
Data Index: 5558760 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.6049. Min Act: -0.1700
Data Index: 4631213 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5736. Min Act: -0.1700
Data Index: 3411226 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5736. Min Act: -0.1700
Data Index: 6075616 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5736. Min Act: -0.1700
Data Index: 7839895 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5736. Min Act: -0.1700
Data Index: 5647807 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5424. Min Act: -0.1700
Data Index: 7856777 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5736. Min Act: -0.1700
Data Index: 3989987 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.6049. Min Act: -0.1700
Data Index: 8211974 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5424. Min Act: -0.1700
Data Index: 6219767 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5111. Min Act: -0.1700
Data Index: 2911673 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5111. Min Act: -0.1700
Data Index: 8397051 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5111. Min Act: -0.1700
Data Index: 7102471 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.5111. Min Act: -0.1700
Data Index: 3994608 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0111. Min Range: -8.0111
Max Act: 7.4799. Min Act: -0.1700
Data Index: 3338280 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19