Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.8206. Min Act: -0.1700
Data Index: 5991396 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.6643. Min Act: -0.1700
Data Index: 4037498 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.6331. Min Act: -0.1700
Data Index: 1620984 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.6018. Min Act: -0.1700
Data Index: 3812214 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.5706. Min Act: -0.1700
Data Index: 7920708 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.5081. Min Act: -0.1700
Data Index: 570456 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.5081. Min Act: -0.1700
Data Index: 6042329 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.5081. Min Act: -0.1700
Data Index: 3498171 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.5393. Min Act: -0.1700
Data Index: 1003395 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.5081. Min Act: -0.1700
Data Index: 3077202 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.5081. Min Act: -0.1700
Data Index: 7378227 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.4768. Min Act: -0.1700
Data Index: 402456 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.4768. Min Act: -0.1700
Data Index: 7873163 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.4768. Min Act: -0.1700
Data Index: 812500 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.4768. Min Act: -0.1700
Data Index: 3162423 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.4768. Min Act: -0.1700
Data Index: 4733696 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.4143. Min Act: -0.1700
Data Index: 4358491 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.4143. Min Act: -0.1700
Data Index: 3880441 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.4143. Min Act: -0.1700
Data Index: 8280141 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8206. Min Range: -4.8206
Max Act: 4.3831. Min Act: -0.1700
Data Index: 330392 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19