Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1270. Min Range: -5.1270
Max Act: 5.1270. Min Act: -0.1700
Data Index: 4419809 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.9395. Min Act: -0.1700
Data Index: 1489371 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.8770. Min Act: -0.1700
Data Index: 1382434 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.8770. Min Act: -0.1700
Data Index: 4918970 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.8458. Min Act: -0.1700
Data Index: 2233116 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.7833. Min Act: -0.1700
Data Index: 7835050 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.7833. Min Act: -0.1700
Data Index: 5108688 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.7833. Min Act: -0.1700
Data Index: 8184185 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.8145. Min Act: -0.1700
Data Index: 4982132 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.7208. Min Act: -0.1700
Data Index: 8202232 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.6895. Min Act: -0.1700
Data Index: 4923500 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.7208. Min Act: -0.1700
Data Index: 2667350 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.7208. Min Act: -0.1700
Data Index: 1694806 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.6583. Min Act: -0.1700
Data Index: 1240404 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.6895. Min Act: -0.1700
Data Index: 4318771 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.6895. Min Act: -0.1700
Data Index: 3717292 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.6895. Min Act: -0.1700
Data Index: 5051802 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.6895. Min Act: -0.1700
Data Index: 5124546 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.6895. Min Act: -0.1700
Data Index: 8669718 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1270. Min Range: -5.1270
Max Act: 4.6583. Min Act: -0.1700
Data Index: 8293637 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19