Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 777 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1350. Min Range: -6.1350
Max Act: 6.1350. Min Act: -0.1700
Data Index: 6963456 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1350. Min Range: -6.1350
Max Act: 6.1037. Min Act: -0.1700
Data Index: 5526685 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1350. Min Range: -6.1350
Max Act: 6.0412. Min Act: -0.1700
Data Index: 5419202 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1350. Min Range: -6.1350
Max Act: 6.0100. Min Act: -0.1700
Data Index: 1634430 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1350. Min Range: -6.1350
Max Act: 6.0412. Min Act: -0.1700
Data Index: 3201603 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.9787. Min Act: -0.1700
Data Index: 4638925 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.9162. Min Act: -0.1700
Data Index: 992289 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.9162. Min Act: -0.1700
Data Index: 5548619 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.7600. Min Act: -0.1700
Data Index: 5388321 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.8225. Min Act: -0.1700
Data Index: 6705207 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.7912. Min Act: -0.1700
Data Index: 7096263 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.7600. Min Act: -0.1700
Data Index: 4681001 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.7600. Min Act: -0.1700
Data Index: 8496691 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.7600. Min Act: -0.1700
Data Index: 6302735 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.7600. Min Act: -0.1700
Data Index: 4415469 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.7287. Min Act: -0.1700
Data Index: 5884142 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.7287. Min Act: -0.1700
Data Index: 2567254 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.7287. Min Act: -0.1700
Data Index: 1587385 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.6975. Min Act: -0.1700
Data Index: 5394090 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1350. Min Range: -6.1350
Max Act: 5.6975. Min Act: -0.1700
Data Index: 3299648 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19