Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 84 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.3771. Min Act: -0.1700
Data Index: 1959449 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.3459. Min Act: -0.1700
Data Index: 1940622 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.2521. Min Act: -0.1700
Data Index: 980148 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.2209. Min Act: -0.1700
Data Index: 1959441 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.2209. Min Act: -0.1700
Data Index: 853879 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.1896. Min Act: -0.1700
Data Index: 772862 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.1584. Min Act: -0.1700
Data Index: 6777202 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.1896. Min Act: -0.1700
Data Index: 2876681 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.1271. Min Act: -0.1700
Data Index: 1879703 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.1271. Min Act: -0.1700
Data Index: 6737723 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.0959. Min Act: -0.1700
Data Index: 252372 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.0646. Min Act: -0.1700
Data Index: 7838183 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.1271. Min Act: -0.1700
Data Index: 478809 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.0646. Min Act: -0.1700
Data Index: 6195167 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.0646. Min Act: -0.1700
Data Index: 1766132 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.0959. Min Act: -0.1700
Data Index: 1318209 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.0021. Min Act: -0.1700
Data Index: 6944692 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.0334. Min Act: -0.1700
Data Index: 1827854 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3771. Min Range: -7.3771
Max Act: 7.0334. Min Act: -0.1700
Data Index: 6992756 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3771. Min Range: -7.3771
Max Act: 6.9709. Min Act: -0.1700
Data Index: 3271428 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19