Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1864. Min Range: -6.1864
Max Act: 6.1864. Min Act: -0.1700
Data Index: 7964345 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1864. Min Range: -6.1864
Max Act: 6.0927. Min Act: -0.1700
Data Index: 8072988 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1864. Min Range: -6.1864
Max Act: 6.0614. Min Act: -0.1700
Data Index: 7580412 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1864. Min Range: -6.1864
Max Act: 6.0302. Min Act: -0.1700
Data Index: 5197486 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1864. Min Range: -6.1864
Max Act: 6.0302. Min Act: -0.1700
Data Index: 6954286 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1864. Min Range: -6.1864
Max Act: 6.0614. Min Act: -0.1700
Data Index: 1634863 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1864. Min Range: -6.1864
Max Act: 6.0302. Min Act: -0.1700
Data Index: 5254351 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9677. Min Act: -0.1700
Data Index: 5263545 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9677. Min Act: -0.1700
Data Index: 2340148 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9677. Min Act: -0.1700
Data Index: 7294542 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9677. Min Act: -0.1700
Data Index: 1248793 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9364. Min Act: -0.1700
Data Index: 2966391 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9364. Min Act: -0.1700
Data Index: 3079876 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9364. Min Act: -0.1700
Data Index: 108783 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9364. Min Act: -0.1700
Data Index: 5836024 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9364. Min Act: -0.1700
Data Index: 5945172 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9364. Min Act: -0.1700
Data Index: 1675711 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9364. Min Act: -0.1700
Data Index: 5476974 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9364. Min Act: -0.1700
Data Index: 4182306 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1864. Min Range: -6.1864
Max Act: 5.9052. Min Act: -0.1700
Data Index: 3932252 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19