Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1026. Min Range: -4.1026
Max Act: 4.1026. Min Act: -0.1700
Data Index: 4418959 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1026. Min Range: -4.1026
Max Act: 4.0714. Min Act: -0.1700
Data Index: 8590511 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.9776. Min Act: -0.1700
Data Index: 8442185 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.9150. Min Act: -0.1700
Data Index: 6834918 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.8838. Min Act: -0.1700
Data Index: 3530044 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.7900. Min Act: -0.1700
Data Index: 2522382 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.7274. Min Act: -0.1700
Data Index: 4414031 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.7274. Min Act: -0.1700
Data Index: 1067433 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.7274. Min Act: -0.1700
Data Index: 3773763 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.7274. Min Act: -0.1700
Data Index: 1947633 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.6961. Min Act: -0.1700
Data Index: 5010071 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.6805. Min Act: -0.1700
Data Index: 1451584 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.6648. Min Act: -0.1700
Data Index: 380956 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.6648. Min Act: -0.1700
Data Index: 7400707 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.6335. Min Act: -0.1700
Data Index: 1163384 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.6492. Min Act: -0.1700
Data Index: 377218 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.6335. Min Act: -0.1700
Data Index: 2660103 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.6335. Min Act: -0.1700
Data Index: 6764992 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.6335. Min Act: -0.1700
Data Index: 6629206 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1026. Min Range: -4.1026
Max Act: 3.6179. Min Act: -0.1700
Data Index: 2052880 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19