Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1149. Min Range: -8.1149
Max Act: 8.1149. Min Act: -0.1700
Data Index: 7187880 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.9899. Min Act: -0.1700
Data Index: 8467019 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.9274. Min Act: -0.1700
Data Index: 3786508 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.9586. Min Act: -0.1700
Data Index: 3970613 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.8336. Min Act: -0.1700
Data Index: 5624997 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.7711. Min Act: -0.1700
Data Index: 5624996 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.7399. Min Act: -0.1700
Data Index: 3175281 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.7399. Min Act: -0.1700
Data Index: 5010896 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.7086. Min Act: -0.1700
Data Index: 3305554 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.6461. Min Act: -0.1700
Data Index: 7344359 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.6774. Min Act: -0.1700
Data Index: 8221663 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.6461. Min Act: -0.1700
Data Index: 6134007 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.6461. Min Act: -0.1700
Data Index: 3468461 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.6461. Min Act: -0.1700
Data Index: 5284907 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.6149. Min Act: -0.1700
Data Index: 2987828 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.4586. Min Act: -0.1700
Data Index: 3924241 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.4274. Min Act: -0.1700
Data Index: 4823189 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.4274. Min Act: -0.1700
Data Index: 3648064 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.4586. Min Act: -0.1700
Data Index: 4852578 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1149. Min Range: -8.1149
Max Act: 7.4274. Min Act: -0.1700
Data Index: 6783278 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19