Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3212 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.5714. Min Act: -0.1700
Data Index: 7532037 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.5553. Min Act: -0.1700
Data Index: 4407820 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.5391. Min Act: -0.1700
Data Index: 4278825 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.5553. Min Act: -0.1700
Data Index: 4543746 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.5068. Min Act: -0.1700
Data Index: 5835289 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4906. Min Act: -0.1700
Data Index: 1540643 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4906. Min Act: -0.1700
Data Index: 7580895 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4743. Min Act: -0.1700
Data Index: 5155316 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4581. Min Act: -0.1700
Data Index: 6982612 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4743. Min Act: -0.1700
Data Index: 391506 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4743. Min Act: -0.1700
Data Index: 4942812 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4743. Min Act: -0.1700
Data Index: 8814958 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4743. Min Act: -0.1700
Data Index: 8118531 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4743. Min Act: -0.1700
Data Index: 5530816 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4743. Min Act: -0.1700
Data Index: 2638572 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4743. Min Act: -0.1700
Data Index: 6215468 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4581. Min Act: -0.1700
Data Index: 6655471 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4581. Min Act: -0.1700
Data Index: 4373432 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4418. Min Act: -0.1700
Data Index: 4581992 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5714. Min Range: -2.5714
Max Act: 2.4256. Min Act: -0.1700
Data Index: 7233641 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19