Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.9010. Min Act: -0.1700
Data Index: 7015244 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.8697. Min Act: -0.1700
Data Index: 8619331 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.8072. Min Act: -0.1700
Data Index: 2679618 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.8228. Min Act: -0.1700
Data Index: 8207023 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.8072. Min Act: -0.1700
Data Index: 4140839 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.8072. Min Act: -0.1700
Data Index: 7095434 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.7133. Min Act: -0.1700
Data Index: 2521511 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.7133. Min Act: -0.1700
Data Index: 8430782 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6977. Min Act: -0.1700
Data Index: 1266956 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6977. Min Act: -0.1700
Data Index: 8456370 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6977. Min Act: -0.1700
Data Index: 1915013 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6820. Min Act: -0.1700
Data Index: 318019 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6507. Min Act: -0.1700
Data Index: 6215521 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6507. Min Act: -0.1700
Data Index: 7545335 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6195. Min Act: -0.1700
Data Index: 5837422 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6038. Min Act: -0.1700
Data Index: 5632049 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6195. Min Act: -0.1700
Data Index: 701097 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6038. Min Act: -0.1700
Data Index: 5748218 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.5881. Min Act: -0.1700
Data Index: 4547337 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9010. Min Range: -3.9010
Max Act: 3.6038. Min Act: -0.1700
Data Index: 3416186 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19