Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2544 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.2214. Min Act: -0.1700
Data Index: 8670078 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.2057. Min Act: -0.1700
Data Index: 1025396 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.2057. Min Act: -0.1700
Data Index: 7678400 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.1742. Min Act: -0.1700
Data Index: 2013263 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.1742. Min Act: -0.1700
Data Index: 6494188 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.1270. Min Act: -0.1700
Data Index: 4931665 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0639. Min Act: -0.1700
Data Index: 6478298 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0797. Min Act: -0.1700
Data Index: 2339836 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0482. Min Act: -0.1700
Data Index: 293714 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0166. Min Act: -0.1700
Data Index: 1369686 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0166. Min Act: -0.1700
Data Index: 5028935 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0166. Min Act: -0.1700
Data Index: 34676 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0166. Min Act: -0.1700
Data Index: 1025395 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2214. Min Range: -3.2214
Max Act: 2.9850. Min Act: -0.1700
Data Index: 1523815 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0008. Min Act: -0.1700
Data Index: 1786304 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0166. Min Act: -0.1700
Data Index: 145491 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0008. Min Act: -0.1700
Data Index: 2624829 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0166. Min Act: -0.1700
Data Index: 2317529 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0008. Min Act: -0.1700
Data Index: 5967835 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2214. Min Range: -3.2214
Max Act: 3.0008. Min Act: -0.1700
Data Index: 7795895 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19