Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1930 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0648. Min Range: -4.0648
Max Act: 4.0335. Min Act: -0.1700
Data Index: 680070 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0648. Min Range: -4.0648
Max Act: 4.0648. Min Act: -0.1700
Data Index: 8818793 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.9710. Min Act: -0.1700
Data Index: 8193469 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.9710. Min Act: -0.1700
Data Index: 3126847 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.9710. Min Act: -0.1700
Data Index: 4571905 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.9085. Min Act: -0.1700
Data Index: 6708432 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8772. Min Act: -0.1700
Data Index: 1445973 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.9397. Min Act: -0.1700
Data Index: 3074270 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.9085. Min Act: -0.1700
Data Index: 3679773 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8772. Min Act: -0.1700
Data Index: 7329046 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8772. Min Act: -0.1700
Data Index: 2997739 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8772. Min Act: -0.1700
Data Index: 6104539 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8772. Min Act: -0.1700
Data Index: 3112211 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8772. Min Act: -0.1700
Data Index: 8495985 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8459. Min Act: -0.1700
Data Index: 2423334 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8459. Min Act: -0.1700
Data Index: 778690 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8147. Min Act: -0.1700
Data Index: 6140912 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8147. Min Act: -0.1700
Data Index: 6307364 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8147. Min Act: -0.1700
Data Index: 1250505 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0648. Min Range: -4.0648
Max Act: 3.8459. Min Act: -0.1700
Data Index: 1443680 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19