Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2864 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1981. Min Range: -7.1981
Max Act: 7.1981. Min Act: -0.1700
Data Index: 4451791 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1981. Min Range: -7.1981
Max Act: 7.1043. Min Act: -0.1700
Data Index: 2489655 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1981. Min Range: -7.1981
Max Act: 7.0418. Min Act: -0.1700
Data Index: 3939134 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.9481. Min Act: -0.1700
Data Index: 4496992 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.9481. Min Act: -0.1700
Data Index: 6315585 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.9793. Min Act: -0.1700
Data Index: 1110116 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.9168. Min Act: -0.1700
Data Index: 5231241 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.9481. Min Act: -0.1700
Data Index: 2960068 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.9168. Min Act: -0.1700
Data Index: 4660161 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.9168. Min Act: -0.1700
Data Index: 7895695 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.8856. Min Act: -0.1700
Data Index: 6985032 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.8856. Min Act: -0.1700
Data Index: 1571899 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.8856. Min Act: -0.1700
Data Index: 4528422 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.8543. Min Act: -0.1700
Data Index: 2671944 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.8543. Min Act: -0.1700
Data Index: 1612905 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.8231. Min Act: -0.1700
Data Index: 7295612 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.8231. Min Act: -0.1700
Data Index: 8049111 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.7918. Min Act: -0.1700
Data Index: 4446368 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.7606. Min Act: -0.1700
Data Index: 4141921 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1981. Min Range: -7.1981
Max Act: 6.7606. Min Act: -0.1700
Data Index: 2188269 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19