Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1658 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0421. Min Range: -5.0421
Max Act: 5.0421. Min Act: -0.1700
Data Index: 6859480 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.7921. Min Act: -0.1700
Data Index: 190066 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.7608. Min Act: -0.1700
Data Index: 3266839 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.7608. Min Act: -0.1700
Data Index: 3412921 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6983. Min Act: -0.1700
Data Index: 7269977 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.7296. Min Act: -0.1700
Data Index: 6193969 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6983. Min Act: -0.1700
Data Index: 7863238 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6671. Min Act: -0.1700
Data Index: 7560396 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6671. Min Act: -0.1700
Data Index: 1027887 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6358. Min Act: -0.1700
Data Index: 4604570 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6671. Min Act: -0.1700
Data Index: 1108686 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6046. Min Act: -0.1700
Data Index: 8261187 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6046. Min Act: -0.1700
Data Index: 4669024 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6046. Min Act: -0.1700
Data Index: 2472760 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6046. Min Act: -0.1700
Data Index: 3562788 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6046. Min Act: -0.1700
Data Index: 1586979 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.6046. Min Act: -0.1700
Data Index: 4264829 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.5733. Min Act: -0.1700
Data Index: 5769688 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.5733. Min Act: -0.1700
Data Index: 652975 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0421. Min Range: -5.0421
Max Act: 4.5421. Min Act: -0.1700
Data Index: 4198838 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19