Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2247 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.4675. Min Act: -0.1700
Data Index: 8738574 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.3425. Min Act: -0.1700
Data Index: 8005887 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.3425. Min Act: -0.1700
Data Index: 4315617 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.3112. Min Act: -0.1700
Data Index: 8825250 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.2175. Min Act: -0.1700
Data Index: 3313089 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.1862. Min Act: -0.1700
Data Index: 291621 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.1550. Min Act: -0.1700
Data Index: 2176232 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.0925. Min Act: -0.1700
Data Index: 4246642 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.0612. Min Act: -0.1700
Data Index: 262487 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.0612. Min Act: -0.1700
Data Index: 7224350 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4675. Min Range: -6.4675
Max Act: 5.9987. Min Act: -0.1700
Data Index: 7224348 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.0300. Min Act: -0.1700
Data Index: 6426431 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.0300. Min Act: -0.1700
Data Index: 5812491 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.0300. Min Act: -0.1700
Data Index: 6074219 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4675. Min Range: -6.4675
Max Act: 6.0300. Min Act: -0.1700
Data Index: 6638792 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4675. Min Range: -6.4675
Max Act: 5.9987. Min Act: -0.1700
Data Index: 3176709 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4675. Min Range: -6.4675
Max Act: 5.9675. Min Act: -0.1700
Data Index: 4298683 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4675. Min Range: -6.4675
Max Act: 5.9675. Min Act: -0.1700
Data Index: 2969942 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4675. Min Range: -6.4675
Max Act: 5.9362. Min Act: -0.1700
Data Index: 4962605 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4675. Min Range: -6.4675
Max Act: 5.9675. Min Act: -0.1700
Data Index: 7191831 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19