Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1169 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.6662. Min Act: -0.1700
Data Index: 1859932 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.4787. Min Act: -0.1700
Data Index: 365343 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.3850. Min Act: -0.1700
Data Index: 1661356 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.3225. Min Act: -0.1700
Data Index: 700266 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.3225. Min Act: -0.1700
Data Index: 3448298 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.3225. Min Act: -0.1700
Data Index: 1035765 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.2600. Min Act: -0.1700
Data Index: 4352098 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.2287. Min Act: -0.1700
Data Index: 1017085 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.1350. Min Act: -0.1700
Data Index: 4724497 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.1662. Min Act: -0.1700
Data Index: 3282495 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.1037. Min Act: -0.1700
Data Index: 911572 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.1037. Min Act: -0.1700
Data Index: 1561800 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.1037. Min Act: -0.1700
Data Index: 811681 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.0412. Min Act: -0.1700
Data Index: 2238452 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.0725. Min Act: -0.1700
Data Index: 3589190 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.0412. Min Act: -0.1700
Data Index: 2238453 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.0412. Min Act: -0.1700
Data Index: 4666897 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6662. Min Range: -7.6662
Max Act: 6.9475. Min Act: -0.1700
Data Index: 5308307 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6662. Min Range: -7.6662
Max Act: 6.9475. Min Act: -0.1700
Data Index: 3952892 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6662. Min Range: -7.6662
Max Act: 7.0100. Min Act: -0.1700
Data Index: 5276612 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19