Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 478 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1116. Min Range: -5.1116
Max Act: 5.1116. Min Act: -0.1700
Data Index: 289458 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1116. Min Range: -5.1116
Max Act: 5.0179. Min Act: -0.1700
Data Index: 7035565 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.8304. Min Act: -0.1700
Data Index: 1887742 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7991. Min Act: -0.1700
Data Index: 8035068 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7991. Min Act: -0.1700
Data Index: 3133446 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7991. Min Act: -0.1700
Data Index: 3244591 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7679. Min Act: -0.1700
Data Index: 625679 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7679. Min Act: -0.1700
Data Index: 3582821 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7679. Min Act: -0.1700
Data Index: 5041055 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7366. Min Act: -0.1700
Data Index: 8067966 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7366. Min Act: -0.1700
Data Index: 7411575 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7054. Min Act: -0.1700
Data Index: 3562013 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7054. Min Act: -0.1700
Data Index: 3433298 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7054. Min Act: -0.1700
Data Index: 4507685 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7054. Min Act: -0.1700
Data Index: 5652218 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7054. Min Act: -0.1700
Data Index: 7606728 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.7054. Min Act: -0.1700
Data Index: 1731502 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.6741. Min Act: -0.1700
Data Index: 1482683 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.6429. Min Act: -0.1700
Data Index: 1342737 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1116. Min Range: -5.1116
Max Act: 4.6741. Min Act: -0.1700
Data Index: 167126 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19