Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 913 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0492. Min Range: -8.0492
Max Act: 8.0492. Min Act: -0.1700
Data Index: 7305094 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0492. Min Range: -8.0492
Max Act: 8.0492. Min Act: -0.1700
Data Index: 6087182 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0492. Min Range: -8.0492
Max Act: 8.0492. Min Act: -0.1700
Data Index: 5112531 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0492. Min Range: -8.0492
Max Act: 8.0492. Min Act: -0.1700
Data Index: 2675049 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.9867. Min Act: -0.1700
Data Index: 80234 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.9242. Min Act: -0.1700
Data Index: 4201623 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.9242. Min Act: -0.1700
Data Index: 8517536 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.9242. Min Act: -0.1700
Data Index: 4379392 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.9242. Min Act: -0.1700
Data Index: 6878745 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.8617. Min Act: -0.1700
Data Index: 6436162 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.8617. Min Act: -0.1700
Data Index: 7030991 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.8617. Min Act: -0.1700
Data Index: 3736399 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.8617. Min Act: -0.1700
Data Index: 3208771 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.8617. Min Act: -0.1700
Data Index: 4702356 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.8617. Min Act: -0.1700
Data Index: 6199051 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.8617. Min Act: -0.1700
Data Index: 6617703 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.8617. Min Act: -0.1700
Data Index: 6452651 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.8617. Min Act: -0.1700
Data Index: 5507942 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.7992. Min Act: -0.1700
Data Index: 2505093 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0492. Min Range: -8.0492
Max Act: 7.7992. Min Act: -0.1700
Data Index: 1984931 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19