Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2311 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.8287. Min Act: -0.1700
Data Index: 4506196 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.5162. Min Act: -0.1700
Data Index: 4654138 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.4537. Min Act: -0.1700
Data Index: 7631260 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.4849. Min Act: -0.1700
Data Index: 6735653 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.4537. Min Act: -0.1700
Data Index: 1465059 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.3599. Min Act: -0.1700
Data Index: 2214142 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.2974. Min Act: -0.1700
Data Index: 152214 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.2974. Min Act: -0.1700
Data Index: 1268167 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.2662. Min Act: -0.1700
Data Index: 5917341 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.2662. Min Act: -0.1700
Data Index: 8720257 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.2662. Min Act: -0.1700
Data Index: 3329050 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.2662. Min Act: -0.1700
Data Index: 5961874 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.2662. Min Act: -0.1700
Data Index: 5411870 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.2037. Min Act: -0.1700
Data Index: 6294056 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.2349. Min Act: -0.1700
Data Index: 2246858 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.1724. Min Act: -0.1700
Data Index: 8033199 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.1724. Min Act: -0.1700
Data Index: 8069317 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.1724. Min Act: -0.1700
Data Index: 1451997 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.1412. Min Act: -0.1700
Data Index: 8484576 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8287. Min Range: -7.8287
Max Act: 7.1099. Min Act: -0.1700
Data Index: 3732162 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19