Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1821 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.8455. Min Act: -0.1700
Data Index: 4284814 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.8143. Min Act: -0.1700
Data Index: 6821855 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.6580. Min Act: -0.1700
Data Index: 8024120 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.2205. Min Act: -0.1700
Data Index: 5469611 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.2205. Min Act: -0.1700
Data Index: 1714008 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.1580. Min Act: -0.1700
Data Index: 36027 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.1893. Min Act: -0.1700
Data Index: 1649947 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.1580. Min Act: -0.1700
Data Index: 4907265 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.1268. Min Act: -0.1700
Data Index: 866085 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.0330. Min Act: -0.1700
Data Index: 4744282 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8455. Min Range: -7.8455
Max Act: 7.0330. Min Act: -0.1700
Data Index: 1053082 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8455. Min Range: -7.8455
Max Act: 6.9705. Min Act: -0.1700
Data Index: 7718469 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8455. Min Range: -7.8455
Max Act: 6.9705. Min Act: -0.1700
Data Index: 2740670 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8455. Min Range: -7.8455
Max Act: 6.9705. Min Act: -0.1700
Data Index: 2534989 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8455. Min Range: -7.8455
Max Act: 6.9393. Min Act: -0.1700
Data Index: 8579179 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8455. Min Range: -7.8455
Max Act: 6.9080. Min Act: -0.1700
Data Index: 632056 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8455. Min Range: -7.8455
Max Act: 6.9393. Min Act: -0.1700
Data Index: 2402864 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8455. Min Range: -7.8455
Max Act: 6.9393. Min Act: -0.1700
Data Index: 5470293 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8455. Min Range: -7.8455
Max Act: 6.9080. Min Act: -0.1700
Data Index: 3547203 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8455. Min Range: -7.8455
Max Act: 6.9393. Min Act: -0.1700
Data Index: 6397768 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19