Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5842 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.8784. Min Act: -0.1700
Data Index: 2119705 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.7846. Min Act: -0.1700
Data Index: 3544993 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.7846. Min Act: -0.1700
Data Index: 8263437 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.7221. Min Act: -0.1700
Data Index: 1699629 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.7221. Min Act: -0.1700
Data Index: 5686261 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.6909. Min Act: -0.1700
Data Index: 4011046 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.6909. Min Act: -0.1700
Data Index: 8231496 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.6284. Min Act: -0.1700
Data Index: 7315468 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.5971. Min Act: -0.1700
Data Index: 589373 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.4721. Min Act: -0.1700
Data Index: 5119096 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.4721. Min Act: -0.1700
Data Index: 5734117 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.4409. Min Act: -0.1700
Data Index: 2529439 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.4409. Min Act: -0.1700
Data Index: 5019308 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.3784. Min Act: -0.1700
Data Index: 4395407 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.3471. Min Act: -0.1700
Data Index: 28330 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.3784. Min Act: -0.1700
Data Index: 6461064 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.3784. Min Act: -0.1700
Data Index: 2921389 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.3471. Min Act: -0.1700
Data Index: 44703 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.3471. Min Act: -0.1700
Data Index: 8057506 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8784. Min Range: -7.8784
Max Act: 7.3471. Min Act: -0.1700
Data Index: 5156863 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19