Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4819 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.4990. Min Act: -0.1700
Data Index: 5113199 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4990. Min Range: -8.4990
Max Act: 8.2177. Min Act: -0.1700
Data Index: 4514158 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.9365. Min Act: -0.1700
Data Index: 7690965 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.7802. Min Act: -0.1700
Data Index: 8352829 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.6552. Min Act: -0.1700
Data Index: 3177627 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.6865. Min Act: -0.1700
Data Index: 3031076 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.6552. Min Act: -0.1700
Data Index: 4289618 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.5927. Min Act: -0.1700
Data Index: 1774034 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.5927. Min Act: -0.1700
Data Index: 3915384 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.5615. Min Act: -0.1700
Data Index: 5604582 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.5615. Min Act: -0.1700
Data Index: 4289619 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.5927. Min Act: -0.1700
Data Index: 2397835 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.4990. Min Act: -0.1700
Data Index: 6181926 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.4990. Min Act: -0.1700
Data Index: 868355 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.4365. Min Act: -0.1700
Data Index: 5711567 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.4990. Min Act: -0.1700
Data Index: 649151 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.4052. Min Act: -0.1700
Data Index: 4225331 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.4365. Min Act: -0.1700
Data Index: 3752918 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.4365. Min Act: -0.1700
Data Index: 1237011 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4990. Min Range: -8.4990
Max Act: 7.4052. Min Act: -0.1700
Data Index: 2527717 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19