Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4141 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3994. Min Range: -8.3994
Max Act: 8.3994. Min Act: -0.1700
Data Index: 6088425 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3994. Min Range: -8.3994
Max Act: 8.1494. Min Act: -0.1700
Data Index: 973758 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.9619. Min Act: -0.1700
Data Index: 2224880 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.9619. Min Act: -0.1700
Data Index: 545134 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.8994. Min Act: -0.1700
Data Index: 7777500 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.8369. Min Act: -0.1700
Data Index: 7742393 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.8057. Min Act: -0.1700
Data Index: 7087089 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.7744. Min Act: -0.1700
Data Index: 4644976 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.7432. Min Act: -0.1700
Data Index: 3536909 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.7119. Min Act: -0.1700
Data Index: 1066649 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.7119. Min Act: -0.1700
Data Index: 8083651 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.6494. Min Act: -0.1700
Data Index: 2424999 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.6182. Min Act: -0.1700
Data Index: 1867061 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.5869. Min Act: -0.1700
Data Index: 1665933 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.5869. Min Act: -0.1700
Data Index: 21905 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.5869. Min Act: -0.1700
Data Index: 7516166 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.5869. Min Act: -0.1700
Data Index: 7944455 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.5557. Min Act: -0.1700
Data Index: 5866872 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.5557. Min Act: -0.1700
Data Index: 1303761 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3994. Min Range: -8.3994
Max Act: 7.5244. Min Act: -0.1700
Data Index: 6670218 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #19