Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 985 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3059. Min Range: -7.3059
Max Act: 7.3059. Min Act: -0.1700
Data Index: 5963686 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3059. Min Range: -7.3059
Max Act: 7.2434. Min Act: -0.1700
Data Index: 6963052 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.9934. Min Act: -0.1700
Data Index: 5924600 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.9934. Min Act: -0.1700
Data Index: 6115832 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.9621. Min Act: -0.1700
Data Index: 7619852 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.9934. Min Act: -0.1700
Data Index: 3501075 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.9621. Min Act: -0.1700
Data Index: 46550 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.8684. Min Act: -0.1700
Data Index: 5800130 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.8371. Min Act: -0.1700
Data Index: 6407904 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.8059. Min Act: -0.1700
Data Index: 3033248 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.7434. Min Act: -0.1700
Data Index: 7075861 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.7434. Min Act: -0.1700
Data Index: 6255006 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.7434. Min Act: -0.1700
Data Index: 6672205 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.7434. Min Act: -0.1700
Data Index: 1088523 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.7434. Min Act: -0.1700
Data Index: 6151084 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.6809. Min Act: -0.1700
Data Index: 6471504 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.7434. Min Act: -0.1700
Data Index: 1900788 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.7434. Min Act: -0.1700
Data Index: 7544592 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.6809. Min Act: -0.1700
Data Index: 7960743 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3059. Min Range: -7.3059
Max Act: 6.6496. Min Act: -0.1700
Data Index: 1950624 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #19