Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.3820. Min Act: -0.1700
Data Index: 4065237 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.2882. Min Act: -0.1700
Data Index: 7966895 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.2257. Min Act: -0.1700
Data Index: 6237767 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.1319. Min Act: -0.1700
Data Index: 2420662 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.1319. Min Act: -0.1700
Data Index: 7523357 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.1007. Min Act: -0.1700
Data Index: 1013320 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.0382. Min Act: -0.1700
Data Index: 7007528 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3820. Min Range: -4.3820
Max Act: 4.0069. Min Act: -0.1700
Data Index: 8812349 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.9756. Min Act: -0.1700
Data Index: 4945824 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.9131. Min Act: -0.1700
Data Index: 389692 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.9444. Min Act: -0.1700
Data Index: 6946488 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.8975. Min Act: -0.1700
Data Index: 1715484 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.8975. Min Act: -0.1700
Data Index: 1563839 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.8662. Min Act: -0.1700
Data Index: 4777188 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.8662. Min Act: -0.1700
Data Index: 8826369 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.8662. Min Act: -0.1700
Data Index: 2283634 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.8662. Min Act: -0.1700
Data Index: 4258591 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.8506. Min Act: -0.1700
Data Index: 217599 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.8506. Min Act: -0.1700
Data Index: 504227 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3820. Min Range: -4.3820
Max Act: 3.8349. Min Act: -0.1700
Data Index: 3470055 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19