Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 497 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.6068. Min Act: -0.1700
Data Index: 400406 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.5907. Min Act: -0.1700
Data Index: 1604436 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.5907. Min Act: -0.1700
Data Index: 1604423 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.5746. Min Act: -0.1700
Data Index: 1604420 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.5423. Min Act: -0.1700
Data Index: 1016898 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.5262. Min Act: -0.1700
Data Index: 6315280 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.5262. Min Act: -0.1700
Data Index: 1604439 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4776. Min Act: -0.1700
Data Index: 1604432 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4938. Min Act: -0.1700
Data Index: 1604430 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4938. Min Act: -0.1700
Data Index: 1604427 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4776. Min Act: -0.1700
Data Index: 1604440 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4613. Min Act: -0.1700
Data Index: 4694853 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4613. Min Act: -0.1700
Data Index: 1604442 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4776. Min Act: -0.1700
Data Index: 1862715 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4613. Min Act: -0.1700
Data Index: 3993509 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4451. Min Act: -0.1700
Data Index: 348083 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4451. Min Act: -0.1700
Data Index: 8385803 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4451. Min Act: -0.1700
Data Index: 1860523 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4288. Min Act: -0.1700
Data Index: 4861836 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6068. Min Range: -2.6068
Max Act: 2.4288. Min Act: -0.1700
Data Index: 6401233 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19