Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.8944. Min Act: -0.1700
Data Index: 1969803 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.8319. Min Act: -0.1700
Data Index: 3547085 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.7694. Min Act: -0.1700
Data Index: 8484491 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.7694. Min Act: -0.1700
Data Index: 7969019 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.7069. Min Act: -0.1700
Data Index: 1922776 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.7069. Min Act: -0.1700
Data Index: 7374715 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.6444. Min Act: -0.1700
Data Index: 5948986 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.5819. Min Act: -0.1700
Data Index: 2137322 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.5194. Min Act: -0.1700
Data Index: 7468791 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.5194. Min Act: -0.1700
Data Index: 8691111 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.3944. Min Act: -0.1700
Data Index: 2263299 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.4569. Min Act: -0.1700
Data Index: 7603213 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.4569. Min Act: -0.1700
Data Index: 2663224 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.4569. Min Act: -0.1700
Data Index: 3443030 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.3944. Min Act: -0.1700
Data Index: 5757253 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.4569. Min Act: -0.1700
Data Index: 6460535 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.3319. Min Act: -0.1700
Data Index: 1918427 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.3944. Min Act: -0.1700
Data Index: 2334536 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.3944. Min Act: -0.1700
Data Index: 5656311 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8944. Min Range: -9.8944
Max Act: 9.3944. Min Act: -0.1700
Data Index: 2954097 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19