Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1344 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.8051. Min Act: -0.1700
Data Index: 6843611 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.8364. Min Act: -0.1700
Data Index: 1431710 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.8051. Min Act: -0.1700
Data Index: 5544786 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.8051. Min Act: -0.1700
Data Index: 4260203 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.7426. Min Act: -0.1700
Data Index: 1135936 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.6801. Min Act: -0.1700
Data Index: 1768581 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.6801. Min Act: -0.1700
Data Index: 3727110 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.6801. Min Act: -0.1700
Data Index: 728480 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.6801. Min Act: -0.1700
Data Index: 3262823 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.6176. Min Act: -0.1700
Data Index: 3076494 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.6489. Min Act: -0.1700
Data Index: 1850849 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.6489. Min Act: -0.1700
Data Index: 2630073 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.5864. Min Act: -0.1700
Data Index: 2471426 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.5864. Min Act: -0.1700
Data Index: 1431704 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.5864. Min Act: -0.1700
Data Index: 2093325 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.6176. Min Act: -0.1700
Data Index: 3081480 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.5551. Min Act: -0.1700
Data Index: 1255594 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.5864. Min Act: -0.1700
Data Index: 4691421 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.5551. Min Act: -0.1700
Data Index: 3035499 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8364. Min Range: -5.8364
Max Act: 5.5551. Min Act: -0.1700
Data Index: 3081482 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19