Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.3975. Min Act: -0.1700
Data Index: 1180750 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.3975. Min Act: -0.1700
Data Index: 727909 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.3037. Min Act: -0.1700
Data Index: 6089288 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.2100. Min Act: -0.1700
Data Index: 1522973 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.2412. Min Act: -0.1700
Data Index: 4559834 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.2100. Min Act: -0.1700
Data Index: 1604930 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.2100. Min Act: -0.1700
Data Index: 3651534 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.2100. Min Act: -0.1700
Data Index: 3972451 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.2100. Min Act: -0.1700
Data Index: 1383326 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.1787. Min Act: -0.1700
Data Index: 5066263 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.1787. Min Act: -0.1700
Data Index: 7553726 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.1787. Min Act: -0.1700
Data Index: 5858955 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.1475. Min Act: -0.1700
Data Index: 3367005 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.1475. Min Act: -0.1700
Data Index: 370530 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.1475. Min Act: -0.1700
Data Index: 5359625 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.1475. Min Act: -0.1700
Data Index: 1911730 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.1475. Min Act: -0.1700
Data Index: 1277508 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.1475. Min Act: -0.1700
Data Index: 1614346 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.0850. Min Act: -0.1700
Data Index: 3637127 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3975. Min Range: -6.3975
Max Act: 6.1162. Min Act: -0.1700
Data Index: 2669036 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19