Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2250. Min Range: -6.2250
Max Act: 6.2250. Min Act: -0.1700
Data Index: 3991029 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2250. Min Range: -6.2250
Max Act: 6.0687. Min Act: -0.1700
Data Index: 8607560 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2250. Min Range: -6.2250
Max Act: 6.0375. Min Act: -0.1700
Data Index: 7071129 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2250. Min Range: -6.2250
Max Act: 6.0375. Min Act: -0.1700
Data Index: 6791257 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2250. Min Range: -6.2250
Max Act: 6.0375. Min Act: -0.1700
Data Index: 8517613 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2250. Min Range: -6.2250
Max Act: 6.0687. Min Act: -0.1700
Data Index: 3306978 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2250. Min Range: -6.2250
Max Act: 6.0062. Min Act: -0.1700
Data Index: 6841225 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.9437. Min Act: -0.1700
Data Index: 6952943 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.9125. Min Act: -0.1700
Data Index: 2956229 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.8812. Min Act: -0.1700
Data Index: 1347535 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.8812. Min Act: -0.1700
Data Index: 3549464 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.8500. Min Act: -0.1700
Data Index: 5742601 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.8187. Min Act: -0.1700
Data Index: 2993961 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.8500. Min Act: -0.1700
Data Index: 508672 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.7875. Min Act: -0.1700
Data Index: 6526198 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.7875. Min Act: -0.1700
Data Index: 4170282 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.7875. Min Act: -0.1700
Data Index: 6631374 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.7875. Min Act: -0.1700
Data Index: 7877221 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.7875. Min Act: -0.1700
Data Index: 5107603 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2250. Min Range: -6.2250
Max Act: 5.7562. Min Act: -0.1700
Data Index: 1302204 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19