Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.6879. Min Act: -0.1700
Data Index: 3381178 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.1879. Min Act: -0.1679
Data Index: 7168622 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.3129. Min Act: -0.1700
Data Index: 937250 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.3129. Min Act: -0.1700
Data Index: 8219643 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.3129. Min Act: -0.1689
Data Index: 777195 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.3129. Min Act: -0.1371
Data Index: 6393567 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.0629. Min Act: -0.1700
Data Index: 817136 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.1879. Min Act: -0.1485
Data Index: 6900591 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.1879. Min Act: -0.1641
Data Index: 7432894 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.1879. Min Act: -0.1700
Data Index: 7955666 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.0629. Min Act: -0.1697
Data Index: 4189875 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.0629. Min Act: -0.1695
Data Index: 1990721 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.1879. Min Act: -0.1700
Data Index: 5532507 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.1879. Min Act: -0.1695
Data Index: 6056429 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.0629. Min Act: -0.1696
Data Index: 6896116 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.0629. Min Act: -0.1699
Data Index: 5641074 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.0629. Min Act: -0.1674
Data Index: 5630871 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.0629. Min Act: -0.1700
Data Index: 1711118 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.0629. Min Act: -0.1085
Data Index: 5254727 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 19.6879. Min Range: -19.6879
Max Act: 19.0629. Min Act: -0.1460
Data Index: 4882853 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #19