Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6339 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.7751. Min Act: -0.1700
Data Index: 8706584 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.5876. Min Act: -0.1700
Data Index: 7005607 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.4001. Min Act: -0.1700
Data Index: 21019 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.3376. Min Act: -0.1700
Data Index: 2310443 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.3064. Min Act: -0.1700
Data Index: 1644233 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.2439. Min Act: -0.1700
Data Index: 8698737 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.2126. Min Act: -0.1700
Data Index: 3407977 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.2126. Min Act: -0.1700
Data Index: 8171225 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.1814. Min Act: -0.1700
Data Index: 2753245 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.2126. Min Act: -0.1700
Data Index: 4250688 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.1501. Min Act: -0.1700
Data Index: 6237557 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.1501. Min Act: -0.1700
Data Index: 4095087 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.1501. Min Act: -0.1700
Data Index: 3214518 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.0876. Min Act: -0.1700
Data Index: 3559805 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.0876. Min Act: -0.1700
Data Index: 233287 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.0564. Min Act: -0.1700
Data Index: 537681 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.0564. Min Act: -0.1700
Data Index: 5399410 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.0251. Min Act: -0.1700
Data Index: 4423865 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.0251. Min Act: -0.1700
Data Index: 7837482 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7751. Min Range: -7.7751
Max Act: 7.0251. Min Act: -0.1700
Data Index: 3658828 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19