Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1739 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.5662. Min Act: -0.1700
Data Index: 6700656 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.5350. Min Act: -0.1700
Data Index: 8792014 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.5037. Min Act: -0.1700
Data Index: 8270425 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.3475. Min Act: -0.1700
Data Index: 3132190 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2225. Min Act: -0.1700
Data Index: 421808 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.2225. Min Act: -0.1700
Data Index: 4978793 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.1600. Min Act: -0.1700
Data Index: 8643798 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.1600. Min Act: -0.1700
Data Index: 4505773 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0975. Min Act: -0.1700
Data Index: 7342445 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0662. Min Act: -0.1700
Data Index: 585019 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0662. Min Act: -0.1700
Data Index: 7843645 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0662. Min Act: -0.1700
Data Index: 4602648 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0350. Min Act: -0.1700
Data Index: 4093152 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0350. Min Act: -0.1700
Data Index: 3794944 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0350. Min Act: -0.1700
Data Index: 2075324 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0350. Min Act: -0.1700
Data Index: 2497907 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5662. Min Range: -6.5662
Max Act: 6.0037. Min Act: -0.1700
Data Index: 6174495 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9725. Min Act: -0.1700
Data Index: 3957124 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9725. Min Act: -0.1700
Data Index: 5554029 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5662. Min Range: -6.5662
Max Act: 5.9412. Min Act: -0.1700
Data Index: 6350940 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19