Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2462 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1760. Min Range: -4.1760
Max Act: 4.1760. Min Act: -0.1700
Data Index: 7646858 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1760. Min Range: -4.1760
Max Act: 4.1760. Min Act: -0.1700
Data Index: 4195488 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1760. Min Range: -4.1760
Max Act: 4.0197. Min Act: -0.1700
Data Index: 8092980 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.9572. Min Act: -0.1700
Data Index: 2658598 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.9572. Min Act: -0.1700
Data Index: 3814683 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.9572. Min Act: -0.1700
Data Index: 7941173 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.9885. Min Act: -0.1700
Data Index: 7512100 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8947. Min Act: -0.1700
Data Index: 1660123 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8947. Min Act: -0.1700
Data Index: 2578680 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8947. Min Act: -0.1700
Data Index: 6176286 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8634. Min Act: -0.1700
Data Index: 7881774 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8947. Min Act: -0.1700
Data Index: 8824693 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8634. Min Act: -0.1700
Data Index: 5421300 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8947. Min Act: -0.1700
Data Index: 612602 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8634. Min Act: -0.1700
Data Index: 5629154 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8634. Min Act: -0.1700
Data Index: 2580729 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8634. Min Act: -0.1700
Data Index: 454630 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8321. Min Act: -0.1700
Data Index: 8104266 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8321. Min Act: -0.1700
Data Index: 12916 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1760. Min Range: -4.1760
Max Act: 3.8321. Min Act: -0.1700
Data Index: 5331790 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19