Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1982 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0770. Min Range: -5.0770
Max Act: 5.0770. Min Act: -0.1700
Data Index: 4855686 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.9833. Min Act: -0.1700
Data Index: 1251295 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.9520. Min Act: -0.1700
Data Index: 7794852 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.9208. Min Act: -0.1700
Data Index: 5034727 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.9208. Min Act: -0.1700
Data Index: 1842769 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.9208. Min Act: -0.1700
Data Index: 4463560 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.8895. Min Act: -0.1700
Data Index: 700026 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.9208. Min Act: -0.1700
Data Index: 2387037 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.8895. Min Act: -0.1700
Data Index: 4690998 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.8583. Min Act: -0.1700
Data Index: 4343022 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.8583. Min Act: -0.1700
Data Index: 6655874 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.7958. Min Act: -0.1700
Data Index: 8143251 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.7333. Min Act: -0.1700
Data Index: 8462981 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.7333. Min Act: -0.1700
Data Index: 4483876 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.7333. Min Act: -0.1700
Data Index: 6592093 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.7333. Min Act: -0.1700
Data Index: 7024670 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.7020. Min Act: -0.1700
Data Index: 1710620 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.6708. Min Act: -0.1700
Data Index: 3213391 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.6708. Min Act: -0.1700
Data Index: 4894776 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0770. Min Range: -5.0770
Max Act: 4.7020. Min Act: -0.1700
Data Index: 3112264 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19