Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.7427. Min Act: -0.1700
Data Index: 7239312 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.6802. Min Act: -0.1700
Data Index: 3375850 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.6802. Min Act: -0.1700
Data Index: 15614 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.6489. Min Act: -0.1700
Data Index: 999555 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.6177. Min Act: -0.1700
Data Index: 4775043 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.6177. Min Act: -0.1700
Data Index: 6833050 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.6177. Min Act: -0.1700
Data Index: 5018622 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.6177. Min Act: -0.1700
Data Index: 3539153 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.5552. Min Act: -0.1700
Data Index: 6282369 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.5552. Min Act: -0.1700
Data Index: 2020637 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.5552. Min Act: -0.1700
Data Index: 3935755 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.5552. Min Act: -0.1700
Data Index: 3262983 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.5552. Min Act: -0.1700
Data Index: 4585376 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.5239. Min Act: -0.1700
Data Index: 6928473 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.4927. Min Act: -0.1700
Data Index: 2522697 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.4927. Min Act: -0.1700
Data Index: 2153374 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.4927. Min Act: -0.1700
Data Index: 1705077 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.4927. Min Act: -0.1700
Data Index: 5355253 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.4927. Min Act: -0.1700
Data Index: 6130494 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7427. Min Range: -4.7427
Max Act: 4.4927. Min Act: -0.1700
Data Index: 6160457 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19