Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3437 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0996. Min Range: -2.0996
Max Act: 2.0996. Min Act: -0.1700
Data Index: 4870751 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0996. Min Range: -2.0996
Max Act: 2.0660. Min Act: -0.1700
Data Index: 6282531 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0996. Min Range: -2.0996
Max Act: 2.0324. Min Act: -0.1700
Data Index: 2774181 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0996. Min Range: -2.0996
Max Act: 2.0492. Min Act: -0.1700
Data Index: 8431440 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0996. Min Range: -2.0996
Max Act: 2.0324. Min Act: -0.1682
Data Index: 2111777 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0996. Min Range: -2.0996
Max Act: 2.0324. Min Act: -0.1700
Data Index: 1462618 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0996. Min Range: -2.0996
Max Act: 2.0492. Min Act: -0.1699
Data Index: 1931986 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0996. Min Range: -2.0996
Max Act: 2.0324. Min Act: -0.1696
Data Index: 8010232 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9986. Min Act: -0.1700
Data Index: 7499558 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9986. Min Act: -0.1700
Data Index: 5362771 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9986. Min Act: -0.1700
Data Index: 7958891 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9986. Min Act: -0.1688
Data Index: 8785773 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9986. Min Act: -0.1700
Data Index: 3445591 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0996. Min Range: -2.0996
Max Act: 2.0155. Min Act: -0.1700
Data Index: 2508611 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9817. Min Act: -0.1700
Data Index: 71777 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9986. Min Act: -0.1699
Data Index: 5457343 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9986. Min Act: -0.1700
Data Index: 4094208 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9817. Min Act: -0.1700
Data Index: 4258035 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9817. Min Act: -0.1700
Data Index: 7952994 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0996. Min Range: -2.0996
Max Act: 1.9817. Min Act: -0.1700
Data Index: 643667 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19