Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3945 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.8197. Min Range: -9.8197
Max Act: 9.3822. Min Act: -0.1700
Data Index: 3066250 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8197. Min Range: -9.8197
Max Act: 9.8197. Min Act: -0.1700
Data Index: 6649559 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.9447. Min Act: -0.1700
Data Index: 1557393 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8197. Min Range: -9.8197
Max Act: 9.3197. Min Act: -0.1700
Data Index: 7560736 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8197. Min Range: -9.8197
Max Act: 9.1322. Min Act: -0.1700
Data Index: 18594 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8197. Min Range: -9.8197
Max Act: 9.4447. Min Act: -0.1700
Data Index: 1185105 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8197. Min Range: -9.8197
Max Act: 9.3197. Min Act: -0.1700
Data Index: 7683890 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.3822. Min Act: -0.1700
Data Index: 3939385 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.8822. Min Act: -0.1700
Data Index: 1177434 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8197. Min Range: -9.8197
Max Act: 9.0697. Min Act: -0.1700
Data Index: 2547774 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.8822. Min Act: -0.1700
Data Index: 3066251 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.7572. Min Act: -0.1700
Data Index: 2695123 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.3197. Min Act: -0.1700
Data Index: 5694516 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.7572. Min Act: -0.1700
Data Index: 710229 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.8197. Min Act: -0.1700
Data Index: 7022910 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.6947. Min Act: -0.1700
Data Index: 952577 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.5072. Min Act: -0.1700
Data Index: 4901273 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.6322. Min Act: -0.1700
Data Index: 5495939 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.6322. Min Act: -0.1700
Data Index: 1842377 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8197. Min Range: -9.8197
Max Act: 8.3822. Min Act: -0.1700
Data Index: 5629557 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19