Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5076 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0891. Min Range: -5.0891
Max Act: 5.0891. Min Act: -0.1700
Data Index: 1720853 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0891. Min Range: -5.0891
Max Act: 5.0578. Min Act: -0.1700
Data Index: 6794 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0891. Min Range: -5.0891
Max Act: 5.0266. Min Act: -0.1700
Data Index: 8195953 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9953. Min Act: -0.1700
Data Index: 410318 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9953. Min Act: -0.1700
Data Index: 5891118 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9641. Min Act: -0.1700
Data Index: 102578 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9641. Min Act: -0.1700
Data Index: 6764851 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9328. Min Act: -0.1700
Data Index: 7014495 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9016. Min Act: -0.1700
Data Index: 3299985 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9016. Min Act: -0.1700
Data Index: 4096281 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9016. Min Act: -0.1700
Data Index: 3586178 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9016. Min Act: -0.1700
Data Index: 7691958 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9016. Min Act: -0.1700
Data Index: 5890467 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9016. Min Act: -0.1700
Data Index: 5672299 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.9016. Min Act: -0.1700
Data Index: 564289 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.8703. Min Act: -0.1700
Data Index: 8142637 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.8703. Min Act: -0.1700
Data Index: 1227824 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.8703. Min Act: -0.1700
Data Index: 3720009 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.8703. Min Act: -0.1700
Data Index: 3731580 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0891. Min Range: -5.0891
Max Act: 4.8703. Min Act: -0.1700
Data Index: 3922674 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19