Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5428 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.6537. Min Act: -0.1700
Data Index: 3197865 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.6381. Min Act: -0.1700
Data Index: 6360827 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.6224. Min Act: -0.1700
Data Index: 8471601 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.6068. Min Act: -0.1700
Data Index: 3406863 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.6068. Min Act: -0.1700
Data Index: 6181200 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.6068. Min Act: -0.1700
Data Index: 6461588 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.6068. Min Act: -0.1700
Data Index: 7143531 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5911. Min Act: -0.1700
Data Index: 5435407 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5755. Min Act: -0.1700
Data Index: 4842657 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5755. Min Act: -0.1700
Data Index: 4143457 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5755. Min Act: -0.1700
Data Index: 8277164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5598. Min Act: -0.1700
Data Index: 309369 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5598. Min Act: -0.1700
Data Index: 7189715 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5598. Min Act: -0.1700
Data Index: 72232 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5598. Min Act: -0.1700
Data Index: 148699 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5598. Min Act: -0.1700
Data Index: 4511974 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5598. Min Act: -0.1700
Data Index: 5100165 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5442. Min Act: -0.1700
Data Index: 3535460 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5285. Min Act: -0.1700
Data Index: 5635591 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6537. Min Range: -3.6537
Max Act: 3.5442. Min Act: -0.1700
Data Index: 751570 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19