Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1711 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3580. Min Range: -5.3580
Max Act: 5.3580. Min Act: -0.1700
Data Index: 5819124 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3580. Min Range: -5.3580
Max Act: 5.2642. Min Act: -0.1700
Data Index: 148155 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.9517. Min Act: -0.1700
Data Index: 4365578 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.9205. Min Act: -0.1700
Data Index: 7999339 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.8580. Min Act: -0.1700
Data Index: 4309075 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.8267. Min Act: -0.1700
Data Index: 1942891 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.8580. Min Act: -0.1700
Data Index: 6371983 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.8267. Min Act: -0.1700
Data Index: 5391959 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.8267. Min Act: -0.1700
Data Index: 3139013 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.8267. Min Act: -0.1700
Data Index: 5473503 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.7955. Min Act: -0.1700
Data Index: 5021712 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.7642. Min Act: -0.1700
Data Index: 7531522 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.7330. Min Act: -0.1700
Data Index: 6111858 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.7330. Min Act: -0.1700
Data Index: 3219093 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.7017. Min Act: -0.1700
Data Index: 4899337 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.6705. Min Act: -0.1700
Data Index: 4909532 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.6705. Min Act: -0.1700
Data Index: 1972884 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.7017. Min Act: -0.1700
Data Index: 452437 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.6705. Min Act: -0.1700
Data Index: 6820134 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3580. Min Range: -5.3580
Max Act: 4.6705. Min Act: -0.1700
Data Index: 2351070 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19