Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2953 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.2235. Min Act: -0.1700
Data Index: 6347337 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.2069. Min Act: -0.1700
Data Index: 2282742 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.1903. Min Act: -0.1700
Data Index: 8816555 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.1570. Min Act: -0.1700
Data Index: 5270119 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.1237. Min Act: -0.1700
Data Index: 3839589 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.1069. Min Act: -0.1700
Data Index: 8516325 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.1069. Min Act: -0.1700
Data Index: 2282740 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0734. Min Act: -0.1700
Data Index: 3998211 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0902. Min Act: -0.1700
Data Index: 2282741 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0734. Min Act: -0.1700
Data Index: 6274604 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0734. Min Act: -0.1700
Data Index: 722278 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.1069. Min Act: -0.1700
Data Index: 7702064 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0734. Min Act: -0.1700
Data Index: 8437648 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0902. Min Act: -0.1700
Data Index: 7948999 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0566. Min Act: -0.1700
Data Index: 5676198 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0734. Min Act: -0.1700
Data Index: 8516324 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0734. Min Act: -0.1700
Data Index: 5426224 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0734. Min Act: -0.1700
Data Index: 8750234 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0734. Min Act: -0.1700
Data Index: 5355655 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2235. Min Range: -2.2235
Max Act: 2.0398. Min Act: -0.1700
Data Index: 3766617 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19