Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1725 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.5459. Min Act: -0.1700
Data Index: 3163218 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.5771. Min Act: -0.1700
Data Index: 8258810 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.5771. Min Act: -0.1700
Data Index: 7836254 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.5459. Min Act: -0.1700
Data Index: 7022433 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.5771. Min Act: -0.1700
Data Index: 7146961 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.4521. Min Act: -0.1700
Data Index: 2992130 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.2959. Min Act: -0.1700
Data Index: 194393 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.1084. Min Act: -0.1700
Data Index: 7805886 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.0146. Min Act: -0.1700
Data Index: 6429344 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.0146. Min Act: -0.1700
Data Index: 6150460 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5771. Min Range: -7.5771
Max Act: 7.0146. Min Act: -0.1700
Data Index: 6150470 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.9834. Min Act: -0.1700
Data Index: 2992133 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.9209. Min Act: -0.1700
Data Index: 4332607 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.8896. Min Act: -0.1700
Data Index: 6106976 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.9209. Min Act: -0.1700
Data Index: 6551127 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.7646. Min Act: -0.1700
Data Index: 5132832 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.7959. Min Act: -0.1700
Data Index: 379853 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.6709. Min Act: -0.1700
Data Index: 6063512 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.6709. Min Act: -0.1700
Data Index: 295831 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5771. Min Range: -7.5771
Max Act: 6.7334. Min Act: -0.1700
Data Index: 7527823 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19