Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3999 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3405. Min Range: -5.3405
Max Act: 5.3405. Min Act: -0.1700
Data Index: 5598817 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3405. Min Range: -5.3405
Max Act: 5.1842. Min Act: -0.1700
Data Index: 2842276 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3405. Min Range: -5.3405
Max Act: 5.1217. Min Act: -0.1700
Data Index: 1029367 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3405. Min Range: -5.3405
Max Act: 5.0592. Min Act: -0.1700
Data Index: 5363932 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3405. Min Range: -5.3405
Max Act: 5.0280. Min Act: -0.1700
Data Index: 5223962 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3405. Min Range: -5.3405
Max Act: 5.0280. Min Act: -0.1700
Data Index: 5933521 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9967. Min Act: -0.1700
Data Index: 5740292 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9967. Min Act: -0.1700
Data Index: 666359 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9655. Min Act: -0.1700
Data Index: 3925189 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9655. Min Act: -0.1700
Data Index: 1949665 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9655. Min Act: -0.1700
Data Index: 4527567 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9655. Min Act: -0.1700
Data Index: 4789271 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9342. Min Act: -0.1700
Data Index: 5845239 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9342. Min Act: -0.1700
Data Index: 8615426 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9030. Min Act: -0.1700
Data Index: 732718 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9030. Min Act: -0.1700
Data Index: 292221 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9030. Min Act: -0.1700
Data Index: 5619608 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9030. Min Act: -0.1700
Data Index: 419329 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9030. Min Act: -0.1700
Data Index: 7599612 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3405. Min Range: -5.3405
Max Act: 4.9030. Min Act: -0.1700
Data Index: 5872271 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19