Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2289. Min Range: -6.2289
Max Act: 6.2289. Min Act: -0.1700
Data Index: 6785179 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2289. Min Range: -6.2289
Max Act: 6.2289. Min Act: -0.1700
Data Index: 6716814 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2289. Min Range: -6.2289
Max Act: 6.1352. Min Act: -0.1700
Data Index: 7581208 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2289. Min Range: -6.2289
Max Act: 6.1664. Min Act: -0.1700
Data Index: 3660279 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2289. Min Range: -6.2289
Max Act: 6.0102. Min Act: -0.1700
Data Index: 561950 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.9477. Min Act: -0.1700
Data Index: 561952 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.9477. Min Act: -0.1700
Data Index: 6129763 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.8852. Min Act: -0.1700
Data Index: 653150 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.8227. Min Act: -0.1700
Data Index: 8466822 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.8227. Min Act: -0.1700
Data Index: 1348820 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.7914. Min Act: -0.1700
Data Index: 435099 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.7602. Min Act: -0.1700
Data Index: 1354977 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.7602. Min Act: -0.1700
Data Index: 2661542 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.7289. Min Act: -0.1700
Data Index: 5254464 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.6977. Min Act: -0.1700
Data Index: 1147138 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.6977. Min Act: -0.1700
Data Index: 3016265 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.6977. Min Act: -0.1700
Data Index: 8110644 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.6664. Min Act: -0.1700
Data Index: 2640125 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.6352. Min Act: -0.1700
Data Index: 561968 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2289. Min Range: -6.2289
Max Act: 5.6664. Min Act: -0.1700
Data Index: 4988185 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19