Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3189 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.5867. Min Act: -0.1700
Data Index: 40866 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.4304. Min Act: -0.1700
Data Index: 8514253 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.3679. Min Act: -0.1700
Data Index: 988456 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.3367. Min Act: -0.1700
Data Index: 607501 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.3367. Min Act: -0.1700
Data Index: 723193 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.2429. Min Act: -0.1700
Data Index: 3933811 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1492. Min Act: -0.1700
Data Index: 8047735 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1804. Min Act: -0.1700
Data Index: 6962192 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1804. Min Act: -0.1700
Data Index: 516015 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1804. Min Act: -0.1700
Data Index: 5199114 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1804. Min Act: -0.1700
Data Index: 8019420 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1804. Min Act: -0.1700
Data Index: 7995678 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1492. Min Act: -0.1700
Data Index: 7179320 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1492. Min Act: -0.1700
Data Index: 5967608 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1492. Min Act: -0.1700
Data Index: 235066 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1179. Min Act: -0.1699
Data Index: 7832767 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1179. Min Act: -0.1700
Data Index: 5353132 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.1179. Min Act: -0.1700
Data Index: 3575473 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.0867. Min Act: -0.1700
Data Index: 1388875 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5867. Min Range: -5.5867
Max Act: 5.0242. Min Act: -0.1700
Data Index: 461845 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19