Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3828 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8154. Min Range: -6.8154
Max Act: 6.8154. Min Act: -0.1700
Data Index: 1067938 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8154. Min Range: -6.8154
Max Act: 6.0342. Min Act: -0.1700
Data Index: 7790961 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.9404. Min Act: -0.1700
Data Index: 2969252 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.9404. Min Act: -0.1700
Data Index: 4506884 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.9092. Min Act: -0.1700
Data Index: 3571056 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.9092. Min Act: -0.1700
Data Index: 3788888 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.8467. Min Act: -0.1700
Data Index: 457189 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.8467. Min Act: -0.1700
Data Index: 5702765 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.8467. Min Act: -0.1700
Data Index: 6830818 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.8467. Min Act: -0.1700
Data Index: 2021945 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.8467. Min Act: -0.1700
Data Index: 882422 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.8467. Min Act: -0.1700
Data Index: 554690 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.8154. Min Act: -0.1700
Data Index: 6872393 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.7842. Min Act: -0.1700
Data Index: 2021946 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.7529. Min Act: -0.1700
Data Index: 3223965 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.7217. Min Act: -0.1700
Data Index: 6422812 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.7217. Min Act: -0.1700
Data Index: 5830467 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.6592. Min Act: -0.1700
Data Index: 4652714 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.6904. Min Act: -0.1700
Data Index: 6470366 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8154. Min Range: -6.8154
Max Act: 5.6279. Min Act: -0.1700
Data Index: 990553 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19