Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4558 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.7349. Min Act: -0.1700
Data Index: 4191448 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.1724. Min Act: -0.1700
Data Index: 7198667 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.1412. Min Act: -0.1700
Data Index: 4577661 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.1099. Min Act: -0.1700
Data Index: 960075 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.0787. Min Act: -0.1700
Data Index: 3731232 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.0474. Min Act: -0.1700
Data Index: 7760244 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.0474. Min Act: -0.1700
Data Index: 1591103 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.0474. Min Act: -0.1700
Data Index: 8649849 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.0162. Min Act: -0.1700
Data Index: 5561420 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7349. Min Range: -6.7349
Max Act: 6.0162. Min Act: -0.1700
Data Index: 1242977 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9537. Min Act: -0.1700
Data Index: 6069965 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9537. Min Act: -0.1700
Data Index: 7105549 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9537. Min Act: -0.1700
Data Index: 6501726 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9224. Min Act: -0.1700
Data Index: 2173892 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9537. Min Act: -0.1700
Data Index: 599224 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9224. Min Act: -0.1700
Data Index: 260378 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9224. Min Act: -0.1700
Data Index: 1361597 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.9224. Min Act: -0.1700
Data Index: 1436193 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.8599. Min Act: -0.1700
Data Index: 2672282 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7349. Min Range: -6.7349
Max Act: 5.8912. Min Act: -0.1700
Data Index: 5620867 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19