Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4045 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9887. Min Act: -0.1700
Data Index: 3574824 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.9412. Min Act: -0.1700
Data Index: 2435217 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.8937. Min Act: -0.1700
Data Index: 5284837 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.8937. Min Act: -0.1700
Data Index: 5535960 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.8778. Min Act: -0.1700
Data Index: 161506 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.8461. Min Act: -0.1700
Data Index: 673696 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7983. Min Act: -0.1700
Data Index: 7146430 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7983. Min Act: -0.1700
Data Index: 8751305 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7824. Min Act: -0.1700
Data Index: 3786751 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7824. Min Act: -0.1700
Data Index: 4954515 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7665. Min Act: -0.1700
Data Index: 8380652 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7824. Min Act: -0.1700
Data Index: 3492699 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7665. Min Act: -0.1700
Data Index: 5291356 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7665. Min Act: -0.1700
Data Index: 2300684 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7505. Min Act: -0.1700
Data Index: 2305284 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7505. Min Act: -0.1700
Data Index: 7461342 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7345. Min Act: -0.1700
Data Index: 1658727 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7505. Min Act: -0.1700
Data Index: 4167088 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7505. Min Act: -0.1700
Data Index: 6093346 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9887. Min Range: -2.9887
Max Act: 2.7824. Min Act: -0.1700
Data Index: 5814752 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19