Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 616 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.4002. Min Act: -0.1700
Data Index: 4402672 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.3512. Min Act: -0.1700
Data Index: 3434300 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.3019. Min Act: -0.1700
Data Index: 2019216 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.2855. Min Act: -0.1700
Data Index: 1600069 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.2360. Min Act: -0.1700
Data Index: 4029065 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.2360. Min Act: -0.1700
Data Index: 1384880 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.2360. Min Act: -0.1700
Data Index: 8212402 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.2028. Min Act: -0.1700
Data Index: 5655273 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.2194. Min Act: -0.1700
Data Index: 2561578 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.2194. Min Act: -0.1700
Data Index: 2641427 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.1862. Min Act: -0.1700
Data Index: 4293687 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.1862. Min Act: -0.1698
Data Index: 7896550 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.2028. Min Act: -0.1700
Data Index: 3272918 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.2028. Min Act: -0.1700
Data Index: 7775655 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.2028. Min Act: -0.1700
Data Index: 8716587 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.1862. Min Act: -0.1700
Data Index: 6590841 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.1862. Min Act: -0.1699
Data Index: 199227 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.1862. Min Act: -0.1700
Data Index: 5624521 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.1696. Min Act: -0.1698
Data Index: 8683935 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4002. Min Range: -2.4002
Max Act: 2.1862. Min Act: -0.1700
Data Index: 4659219 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19