Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5476 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.8965. Min Act: -0.1700
Data Index: 7193218 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.8028. Min Act: -0.1700
Data Index: 582839 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.7403. Min Act: -0.1700
Data Index: 288566 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.7090. Min Act: -0.1700
Data Index: 8822337 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.6465. Min Act: -0.1700
Data Index: 1075436 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.6465. Min Act: -0.1700
Data Index: 5101153 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5840. Min Act: -0.1700
Data Index: 1582698 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5528. Min Act: -0.1700
Data Index: 5049154 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5528. Min Act: -0.1700
Data Index: 8256033 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5528. Min Act: -0.1700
Data Index: 6695046 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5528. Min Act: -0.1700
Data Index: 4460542 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5528. Min Act: -0.1700
Data Index: 3828546 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5528. Min Act: -0.1700
Data Index: 1791436 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5528. Min Act: -0.1700
Data Index: 8825595 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5215. Min Act: -0.1700
Data Index: 4119591 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5215. Min Act: -0.1700
Data Index: 7712307 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.5215. Min Act: -0.1700
Data Index: 2215972 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.4903. Min Act: -0.1700
Data Index: 555469 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.4903. Min Act: -0.1700
Data Index: 998731 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8965. Min Range: -5.8965
Max Act: 5.4903. Min Act: -0.1700
Data Index: 5159301 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19