Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 739 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.5958. Min Act: -0.1700
Data Index: 7954165 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.3458. Min Act: -0.1700
Data Index: 3712149 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.3458. Min Act: -0.1700
Data Index: 1150945 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.2520. Min Act: -0.1700
Data Index: 7068088 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.3145. Min Act: -0.1700
Data Index: 1655968 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.2208. Min Act: -0.1700
Data Index: 5931634 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.1583. Min Act: -0.1700
Data Index: 2815048 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.1270. Min Act: -0.1700
Data Index: 226187 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0958. Min Act: -0.1700
Data Index: 1938617 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0958. Min Act: -0.1700
Data Index: 2378252 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5958. Min Range: -5.5958
Max Act: 5.0333. Min Act: -0.1700
Data Index: 8105649 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5958. Min Range: -5.5958
Max Act: 4.9708. Min Act: -0.1700
Data Index: 8814471 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5958. Min Range: -5.5958
Max Act: 4.9395. Min Act: -0.1700
Data Index: 8002655 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5958. Min Range: -5.5958
Max Act: 4.9395. Min Act: -0.1700
Data Index: 6076609 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5958. Min Range: -5.5958
Max Act: 4.9395. Min Act: -0.1700
Data Index: 2517055 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5958. Min Range: -5.5958
Max Act: 4.9083. Min Act: -0.1700
Data Index: 6120117 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5958. Min Range: -5.5958
Max Act: 4.9083. Min Act: -0.1700
Data Index: 4035149 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5958. Min Range: -5.5958
Max Act: 4.9083. Min Act: -0.1700
Data Index: 7674724 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5958. Min Range: -5.5958
Max Act: 4.9083. Min Act: -0.1700
Data Index: 4398817 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5958. Min Range: -5.5958
Max Act: 4.8770. Min Act: -0.1700
Data Index: 1173948 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19