Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 664 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3299. Min Range: -4.3299
Max Act: 4.3299. Min Act: -0.1700
Data Index: 6421656 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3299. Min Range: -4.3299
Max Act: 4.2049. Min Act: -0.1700
Data Index: 2024101 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3299. Min Range: -4.3299
Max Act: 4.1424. Min Act: -0.1700
Data Index: 3508204 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3299. Min Range: -4.3299
Max Act: 4.1424. Min Act: -0.1700
Data Index: 7167773 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3299. Min Range: -4.3299
Max Act: 4.0174. Min Act: -0.1700
Data Index: 6877056 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.9861. Min Act: -0.1700
Data Index: 3303290 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.9236. Min Act: -0.1700
Data Index: 6421654 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.9236. Min Act: -0.1700
Data Index: 985390 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.9236. Min Act: -0.1700
Data Index: 4095897 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.8923. Min Act: -0.1700
Data Index: 4220228 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.8611. Min Act: -0.1700
Data Index: 3508203 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.8611. Min Act: -0.1700
Data Index: 5417583 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.8611. Min Act: -0.1700
Data Index: 985391 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.7985. Min Act: -0.1700
Data Index: 6370497 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.7985. Min Act: -0.1700
Data Index: 1372116 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.7985. Min Act: -0.1700
Data Index: 6508486 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.7985. Min Act: -0.1700
Data Index: 4092157 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.7672. Min Act: -0.1700
Data Index: 199548 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.7672. Min Act: -0.1700
Data Index: 3381852 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3299. Min Range: -4.3299
Max Act: 3.7672. Min Act: -0.1700
Data Index: 4040234 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19