Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3405 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2861. Min Range: -7.2861
Max Act: 7.2861. Min Act: -0.1700
Data Index: 8459453 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2861. Min Range: -7.2861
Max Act: 7.0049. Min Act: -0.1700
Data Index: 4500795 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2861. Min Range: -7.2861
Max Act: 7.0361. Min Act: -0.1700
Data Index: 1481930 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.9736. Min Act: -0.1700
Data Index: 2201559 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.8799. Min Act: -0.1700
Data Index: 7658396 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.8486. Min Act: -0.1700
Data Index: 383954 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.8174. Min Act: -0.1700
Data Index: 330728 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.7861. Min Act: -0.1700
Data Index: 7445545 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.7861. Min Act: -0.1700
Data Index: 7884979 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.7861. Min Act: -0.1700
Data Index: 6787282 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.7236. Min Act: -0.1700
Data Index: 917302 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.7549. Min Act: -0.1700
Data Index: 5685109 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.7549. Min Act: -0.1700
Data Index: 6629226 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.6924. Min Act: -0.1700
Data Index: 785206 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.7236. Min Act: -0.1700
Data Index: 4518481 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.7236. Min Act: -0.1700
Data Index: 2758129 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.7236. Min Act: -0.1700
Data Index: 6056688 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.7236. Min Act: -0.1700
Data Index: 8675214 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.6924. Min Act: -0.1700
Data Index: 1656780 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2861. Min Range: -7.2861
Max Act: 6.6924. Min Act: -0.1700
Data Index: 963417 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #19