Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2000. Min Range: -5.2000
Max Act: 5.2000. Min Act: -0.1700
Data Index: 6284065 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2000. Min Range: -5.2000
Max Act: 5.1688. Min Act: -0.1700
Data Index: 5931206 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2000. Min Range: -5.2000
Max Act: 5.1063. Min Act: -0.1700
Data Index: 4609971 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2000. Min Range: -5.2000
Max Act: 5.0750. Min Act: -0.1700
Data Index: 6392705 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2000. Min Range: -5.2000
Max Act: 5.0438. Min Act: -0.1700
Data Index: 4958068 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2000. Min Range: -5.2000
Max Act: 5.1063. Min Act: -0.1700
Data Index: 28103 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2000. Min Range: -5.2000
Max Act: 5.0125. Min Act: -0.1700
Data Index: 4925606 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2000. Min Range: -5.2000
Max Act: 5.0125. Min Act: -0.1700
Data Index: 1326663 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.9813. Min Act: -0.1700
Data Index: 8498860 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.9813. Min Act: -0.1700
Data Index: 5920622 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.9500. Min Act: -0.1700
Data Index: 4119697 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.9188. Min Act: -0.1700
Data Index: 2018064 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.9188. Min Act: -0.1700
Data Index: 6077333 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.8875. Min Act: -0.1700
Data Index: 7238016 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.8563. Min Act: -0.1700
Data Index: 6180411 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.8563. Min Act: -0.1700
Data Index: 397836 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.8563. Min Act: -0.1700
Data Index: 677359 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.8250. Min Act: -0.1700
Data Index: 4524064 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.8563. Min Act: -0.1700
Data Index: 7473615 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2000. Min Range: -5.2000
Max Act: 4.8250. Min Act: -0.1700
Data Index: 3335854 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19