Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1638 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.4868. Min Act: -0.1700
Data Index: 6362092 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.3618. Min Act: -0.1700
Data Index: 8392854 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.3306. Min Act: -0.1700
Data Index: 1892927 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.2368. Min Act: -0.1700
Data Index: 211 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.0806. Min Act: -0.1700
Data Index: 8404614 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.0806. Min Act: -0.1700
Data Index: 1438687 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.0806. Min Act: -0.1700
Data Index: 5306817 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.0493. Min Act: -0.1700
Data Index: 1191207 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.0493. Min Act: -0.1700
Data Index: 7997096 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.0806. Min Act: -0.1700
Data Index: 5443441 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4868. Min Range: -6.4868
Max Act: 6.0181. Min Act: -0.1700
Data Index: 763648 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4868. Min Range: -6.4868
Max Act: 5.9868. Min Act: -0.1700
Data Index: 3971726 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4868. Min Range: -6.4868
Max Act: 5.9556. Min Act: -0.1700
Data Index: 2779127 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4868. Min Range: -6.4868
Max Act: 5.9556. Min Act: -0.1700
Data Index: 2465221 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4868. Min Range: -6.4868
Max Act: 5.9243. Min Act: -0.1700
Data Index: 4411525 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4868. Min Range: -6.4868
Max Act: 5.8306. Min Act: -0.1700
Data Index: 7855917 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4868. Min Range: -6.4868
Max Act: 5.8618. Min Act: -0.1700
Data Index: 4848003 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4868. Min Range: -6.4868
Max Act: 5.8306. Min Act: -0.1700
Data Index: 1192469 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4868. Min Range: -6.4868
Max Act: 5.8306. Min Act: -0.1700
Data Index: 733019 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4868. Min Range: -6.4868
Max Act: 5.8306. Min Act: -0.1700
Data Index: 8165402 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19