Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1876 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1363. Min Range: -5.1363
Max Act: 5.1363. Min Act: -0.1700
Data Index: 5980695 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.9488. Min Act: -0.1700
Data Index: 8816174 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8863. Min Act: -0.1700
Data Index: 7301603 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.9176. Min Act: -0.1700
Data Index: 2776872 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8551. Min Act: -0.1700
Data Index: 6099639 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8551. Min Act: -0.1700
Data Index: 835193 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8551. Min Act: -0.1700
Data Index: 6593539 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 513078 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 3398381 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 5738852 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.7926. Min Act: -0.1700
Data Index: 3198877 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.7926. Min Act: -0.1700
Data Index: 2772007 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 7751449 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 2320346 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.8238. Min Act: -0.1700
Data Index: 6057936 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.7926. Min Act: -0.1700
Data Index: 2179831 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.7926. Min Act: -0.1700
Data Index: 4333364 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.7926. Min Act: -0.1700
Data Index: 7229614 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.7926. Min Act: -0.1700
Data Index: 1581181 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1363. Min Range: -5.1363
Max Act: 4.7613. Min Act: -0.1700
Data Index: 6932563 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #19