Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2796 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.9235. Min Act: -0.1700
Data Index: 3641689 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.7985. Min Act: -0.1700
Data Index: 7401579 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.6110. Min Act: -0.1700
Data Index: 2976357 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.4860. Min Act: -0.1700
Data Index: 4790158 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.3610. Min Act: -0.1700
Data Index: 585967 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.3610. Min Act: -0.1700
Data Index: 6332602 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.3610. Min Act: -0.1700
Data Index: 3078407 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.2985. Min Act: -0.1700
Data Index: 931031 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.2360. Min Act: -0.1700
Data Index: 7513504 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.2985. Min Act: -0.1700
Data Index: 1574385 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.2985. Min Act: -0.1700
Data Index: 2762072 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.2360. Min Act: -0.1700
Data Index: 1150340 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.2360. Min Act: -0.1700
Data Index: 2290667 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.2360. Min Act: -0.1700
Data Index: 3557097 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.2360. Min Act: -0.1700
Data Index: 7433206 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.1735. Min Act: -0.1700
Data Index: 2716305 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.1735. Min Act: -0.1700
Data Index: 3309524 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.2360. Min Act: -0.1700
Data Index: 4544497 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.1110. Min Act: -0.1700
Data Index: 714674 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9235. Min Range: -10.9235
Max Act: 10.1110. Min Act: -0.1700
Data Index: 905709 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19