Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4062 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0711. Min Act: -0.1700
Data Index: 6758694 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0711. Min Act: -0.1700
Data Index: 511514 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0398. Min Act: -0.1700
Data Index: 5308471 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9773. Min Act: -0.1700
Data Index: 7730521 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9773. Min Act: -0.1700
Data Index: 8512951 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9460. Min Act: -0.1700
Data Index: 8367431 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9460. Min Act: -0.1700
Data Index: 2175405 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9148. Min Act: -0.1700
Data Index: 6543997 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9460. Min Act: -0.1700
Data Index: 8512952 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9460. Min Act: -0.1700
Data Index: 5744258 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9148. Min Act: -0.1700
Data Index: 4434049 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9460. Min Act: -0.1700
Data Index: 1774033 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.8991. Min Act: -0.1700
Data Index: 3936748 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.8991. Min Act: -0.1700
Data Index: 3283821 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.8991. Min Act: -0.1700
Data Index: 3170418 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.8679. Min Act: -0.1700
Data Index: 6993130 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.8835. Min Act: -0.1700
Data Index: 6588120 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.8835. Min Act: -0.1700
Data Index: 1534850 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.8835. Min Act: -0.1700
Data Index: 8766160 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.8522. Min Act: -0.1700
Data Index: 978554 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19