Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2893 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0734. Min Range: -7.0734
Max Act: 7.0734. Min Act: -0.1700
Data Index: 652055 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.5734. Min Act: -0.1700
Data Index: 4082046 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.5421. Min Act: -0.1700
Data Index: 7194833 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.5109. Min Act: -0.1700
Data Index: 3396600 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.3859. Min Act: -0.1700
Data Index: 8095581 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.3859. Min Act: -0.1700
Data Index: 1320809 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.3546. Min Act: -0.1700
Data Index: 7641451 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.3546. Min Act: -0.1700
Data Index: 3365191 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.3234. Min Act: -0.1700
Data Index: 4025560 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.2921. Min Act: -0.1700
Data Index: 6089848 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.2921. Min Act: -0.1700
Data Index: 2699085 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.2609. Min Act: -0.1700
Data Index: 7641463 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.2609. Min Act: -0.1700
Data Index: 7637323 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.2296. Min Act: -0.1700
Data Index: 3957508 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.2296. Min Act: -0.1700
Data Index: 2259936 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.2296. Min Act: -0.1700
Data Index: 4352604 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.1984. Min Act: -0.1700
Data Index: 1932850 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.1984. Min Act: -0.1700
Data Index: 4844705 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.1671. Min Act: -0.1700
Data Index: 2155235 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0734. Min Range: -7.0734
Max Act: 6.1984. Min Act: -0.1700
Data Index: 3249084 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19