Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0608. Min Range: -4.0608
Max Act: 4.0608. Min Act: -0.1700
Data Index: 5223755 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.9983. Min Act: -0.1700
Data Index: 888613 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.9670. Min Act: -0.1700
Data Index: 2712987 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.9045. Min Act: -0.1700
Data Index: 2811821 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.9201. Min Act: -0.1700
Data Index: 3521904 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.8420. Min Act: -0.1700
Data Index: 609784 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.8732. Min Act: -0.1700
Data Index: 2388742 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.8420. Min Act: -0.1700
Data Index: 5321504 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.8263. Min Act: -0.1700
Data Index: 2400457 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7951. Min Act: -0.1700
Data Index: 8343849 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7951. Min Act: -0.1700
Data Index: 4496722 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7951. Min Act: -0.1700
Data Index: 7488991 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7638. Min Act: -0.1700
Data Index: 1182509 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7794. Min Act: -0.1700
Data Index: 328270 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7482. Min Act: -0.1700
Data Index: 274547 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7482. Min Act: -0.1700
Data Index: 8187199 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7482. Min Act: -0.1700
Data Index: 7862000 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7169. Min Act: -0.1700
Data Index: 5704695 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7482. Min Act: -0.1700
Data Index: 7048387 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0608. Min Range: -4.0608
Max Act: 3.7325. Min Act: -0.1700
Data Index: 2146892 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19