Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4879 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3146. Min Range: -8.3146
Max Act: 8.3146. Min Act: -0.1700
Data Index: 94621 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3146. Min Range: -8.3146
Max Act: 8.0646. Min Act: -0.1700
Data Index: 1543359 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3146. Min Range: -8.3146
Max Act: 8.0021. Min Act: -0.1700
Data Index: 382227 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.9396. Min Act: -0.1700
Data Index: 4248913 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.8146. Min Act: -0.1700
Data Index: 3733563 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.7209. Min Act: -0.1700
Data Index: 1586134 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.6896. Min Act: -0.1700
Data Index: 5288016 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.6896. Min Act: -0.1700
Data Index: 7805397 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.6584. Min Act: -0.1700
Data Index: 3487502 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.6271. Min Act: -0.1700
Data Index: 6564315 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.6271. Min Act: -0.1700
Data Index: 1729015 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.6271. Min Act: -0.1700
Data Index: 7708059 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.5959. Min Act: -0.1700
Data Index: 8476615 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.5334. Min Act: -0.1700
Data Index: 5830255 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.5334. Min Act: -0.1700
Data Index: 8680462 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.5021. Min Act: -0.1700
Data Index: 2395857 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.5021. Min Act: -0.1700
Data Index: 1630890 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.5021. Min Act: -0.1700
Data Index: 2360137 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.5021. Min Act: -0.1700
Data Index: 3314236 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3146. Min Range: -8.3146
Max Act: 7.5021. Min Act: -0.1700
Data Index: 7134052 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19