Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5154 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2942. Min Range: -6.2942
Max Act: 6.2942. Min Act: -0.1700
Data Index: 1323726 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2942. Min Range: -6.2942
Max Act: 6.2630. Min Act: -0.1700
Data Index: 4960960 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2942. Min Range: -6.2942
Max Act: 6.2005. Min Act: -0.1700
Data Index: 8229397 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2942. Min Range: -6.2942
Max Act: 6.1380. Min Act: -0.1700
Data Index: 432432 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2942. Min Range: -6.2942
Max Act: 6.0755. Min Act: -0.1700
Data Index: 8446082 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2942. Min Range: -6.2942
Max Act: 6.0442. Min Act: -0.1700
Data Index: 595216 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.9817. Min Act: -0.1700
Data Index: 8088254 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.9505. Min Act: -0.1700
Data Index: 6069172 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.9505. Min Act: -0.1700
Data Index: 535374 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.8880. Min Act: -0.1700
Data Index: 164477 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.8880. Min Act: -0.1700
Data Index: 3814140 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.8880. Min Act: -0.1700
Data Index: 5508882 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.8567. Min Act: -0.1700
Data Index: 6052320 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.8255. Min Act: -0.1700
Data Index: 1628958 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.7942. Min Act: -0.1700
Data Index: 1302027 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.7942. Min Act: -0.1700
Data Index: 1035116 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.7942. Min Act: -0.1700
Data Index: 1067441 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.7630. Min Act: -0.1700
Data Index: 7680807 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.7630. Min Act: -0.1700
Data Index: 7776737 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2942. Min Range: -6.2942
Max Act: 5.7630. Min Act: -0.1700
Data Index: 6052317 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #19