Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3013 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0668. Min Range: -4.0668
Max Act: 4.0668. Min Act: -0.1700
Data Index: 2015505 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.8479. Min Act: -0.1700
Data Index: 3145864 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.8167. Min Act: -0.1700
Data Index: 2054805 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.7854. Min Act: -0.1700
Data Index: 1223520 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.7541. Min Act: -0.1700
Data Index: 8546702 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.7541. Min Act: -0.1700
Data Index: 4152064 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.7072. Min Act: -0.1700
Data Index: 1164694 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6916. Min Act: -0.1700
Data Index: 4435439 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6916. Min Act: -0.1700
Data Index: 7650091 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6916. Min Act: -0.1700
Data Index: 5236576 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6916. Min Act: -0.1700
Data Index: 8261406 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6759. Min Act: -0.1700
Data Index: 7709164 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6603. Min Act: -0.1700
Data Index: 8678630 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6290. Min Act: -0.1700
Data Index: 5364469 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6133. Min Act: -0.1700
Data Index: 5221812 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6133. Min Act: -0.1700
Data Index: 6247632 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6133. Min Act: -0.1700
Data Index: 5910555 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6133. Min Act: -0.1700
Data Index: 2734538 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6133. Min Act: -0.1700
Data Index: 1285292 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0668. Min Range: -4.0668
Max Act: 3.6133. Min Act: -0.1700
Data Index: 1384840 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19