Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6123 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.6787. Min Act: -0.1700
Data Index: 5196588 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.5850. Min Act: -0.1700
Data Index: 1523014 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.3662. Min Act: -0.1700
Data Index: 6159495 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.3662. Min Act: -0.1700
Data Index: 5648134 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.3662. Min Act: -0.1700
Data Index: 4808400 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.3037. Min Act: -0.1700
Data Index: 8444450 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.3350. Min Act: -0.1700
Data Index: 3910728 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.3350. Min Act: -0.1700
Data Index: 5798100 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.3037. Min Act: -0.1700
Data Index: 2049905 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.3037. Min Act: -0.1700
Data Index: 3720849 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.3350. Min Act: -0.1700
Data Index: 464092 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.3037. Min Act: -0.1700
Data Index: 1571619 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.2725. Min Act: -0.1700
Data Index: 5756741 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.2725. Min Act: -0.1700
Data Index: 185236 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.2725. Min Act: -0.1700
Data Index: 2555432 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.2725. Min Act: -0.1700
Data Index: 981310 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.2412. Min Act: -0.1700
Data Index: 7994642 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.2412. Min Act: -0.1700
Data Index: 3234186 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.2412. Min Act: -0.1700
Data Index: 1382105 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6787. Min Range: -5.6787
Max Act: 5.2412. Min Act: -0.1700
Data Index: 6230648 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19