Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 967 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3524. Min Range: -9.3524
Max Act: 9.3524. Min Act: -0.1700
Data Index: 4464312 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3524. Min Range: -9.3524
Max Act: 9.1024. Min Act: -0.1700
Data Index: 1852973 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3524. Min Range: -9.3524
Max Act: 9.1024. Min Act: -0.1700
Data Index: 6996331 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3524. Min Range: -9.3524
Max Act: 9.1024. Min Act: -0.1700
Data Index: 5651414 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3524. Min Range: -9.3524
Max Act: 9.1024. Min Act: -0.1700
Data Index: 3747163 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.9774. Min Act: -0.1700
Data Index: 5562039 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.9149. Min Act: -0.1700
Data Index: 4458992 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.9149. Min Act: -0.1700
Data Index: 3925148 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.8524. Min Act: -0.1700
Data Index: 465451 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.8524. Min Act: -0.1700
Data Index: 5716995 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.8524. Min Act: -0.1700
Data Index: 2977771 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.7274. Min Act: -0.1700
Data Index: 7759470 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.7274. Min Act: -0.1700
Data Index: 5951109 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.7274. Min Act: -0.1700
Data Index: 6090870 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.6649. Min Act: -0.1700
Data Index: 7306313 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.7274. Min Act: -0.1700
Data Index: 4838069 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.6649. Min Act: -0.1700
Data Index: 4206890 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.6649. Min Act: -0.1700
Data Index: 5171402 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.6024. Min Act: -0.1700
Data Index: 4174055 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3524. Min Range: -9.3524
Max Act: 8.6649. Min Act: -0.1700
Data Index: 1389764 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19