Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2834. Min Range: -8.2834
Max Act: 8.2834. Min Act: -0.1700
Data Index: 2902554 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2834. Min Range: -8.2834
Max Act: 8.1584. Min Act: -0.1700
Data Index: 4458604 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.9084. Min Act: -0.1700
Data Index: 2564509 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.8771. Min Act: -0.1700
Data Index: 7185172 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.8771. Min Act: -0.1700
Data Index: 5827283 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.6271. Min Act: -0.1700
Data Index: 8745204 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.5646. Min Act: -0.1700
Data Index: 2125624 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.5646. Min Act: -0.1700
Data Index: 2020275 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.5646. Min Act: -0.1700
Data Index: 5366489 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.4709. Min Act: -0.1700
Data Index: 6271486 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.4709. Min Act: -0.1700
Data Index: 3118368 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.4084. Min Act: -0.1700
Data Index: 997814 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.4396. Min Act: -0.1700
Data Index: 2217086 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.3146. Min Act: -0.1700
Data Index: 2332554 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.3146. Min Act: -0.1699
Data Index: 4558879 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.3146. Min Act: -0.1700
Data Index: 7334933 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.3146. Min Act: -0.1700
Data Index: 8481454 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.3146. Min Act: -0.1700
Data Index: 4749065 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.2521. Min Act: -0.1700
Data Index: 1412710 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2834. Min Range: -8.2834
Max Act: 7.2834. Min Act: -0.1700
Data Index: 5607197 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19