Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2794 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.8452. Min Act: -0.1700
Data Index: 946662 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.6577. Min Act: -0.1700
Data Index: 1255778 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.6264. Min Act: -0.1700
Data Index: 7522173 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.5952. Min Act: -0.1700
Data Index: 253463 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.5327. Min Act: -0.1700
Data Index: 3326061 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.5639. Min Act: -0.1700
Data Index: 5644504 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.5014. Min Act: -0.1700
Data Index: 7639583 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.5014. Min Act: -0.1700
Data Index: 7166748 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.4389. Min Act: -0.1700
Data Index: 7247448 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.4389. Min Act: -0.1700
Data Index: 1593820 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.3764. Min Act: -0.1700
Data Index: 4408160 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.4077. Min Act: -0.1700
Data Index: 3180269 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.4389. Min Act: -0.1700
Data Index: 8643695 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.4077. Min Act: -0.1700
Data Index: 7219106 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.3764. Min Act: -0.1700
Data Index: 5851959 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.3764. Min Act: -0.1700
Data Index: 3591463 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.3764. Min Act: -0.1700
Data Index: 5575807 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.3764. Min Act: -0.1700
Data Index: 1124899 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.3764. Min Act: -0.1700
Data Index: 2828005 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8452. Min Range: -5.8452
Max Act: 5.3764. Min Act: -0.1700
Data Index: 115531 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19