Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1269. Min Range: -4.1269
Max Act: 4.1269. Min Act: -0.1700
Data Index: 3563210 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1269. Min Range: -4.1269
Max Act: 4.1269. Min Act: -0.1700
Data Index: 3799203 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1269. Min Range: -4.1269
Max Act: 4.0644. Min Act: -0.1700
Data Index: 7110282 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1269. Min Range: -4.1269
Max Act: 4.0331. Min Act: -0.1700
Data Index: 969514 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1269. Min Range: -4.1269
Max Act: 4.0331. Min Act: -0.1700
Data Index: 4862102 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1269. Min Range: -4.1269
Max Act: 4.0644. Min Act: -0.1700
Data Index: 8525454 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1269. Min Range: -4.1269
Max Act: 4.0331. Min Act: -0.1700
Data Index: 7895595 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.9081. Min Act: -0.1700
Data Index: 8657534 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.8768. Min Act: -0.1700
Data Index: 322748 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.8768. Min Act: -0.1700
Data Index: 3857210 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.8768. Min Act: -0.1700
Data Index: 5401385 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.8768. Min Act: -0.1700
Data Index: 5155390 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.8456. Min Act: -0.1700
Data Index: 2687769 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.8299. Min Act: -0.1700
Data Index: 5439208 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.8299. Min Act: -0.1700
Data Index: 5028477 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.8299. Min Act: -0.1700
Data Index: 6938634 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.8299. Min Act: -0.1700
Data Index: 1079691 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.7987. Min Act: -0.1700
Data Index: 8247878 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.7987. Min Act: -0.1700
Data Index: 5534395 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1269. Min Range: -4.1269
Max Act: 3.7674. Min Act: -0.1700
Data Index: 6350075 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19