Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3917 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3065. Min Range: -6.3065
Max Act: 6.3065. Min Act: -0.1700
Data Index: 4910032 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3065. Min Range: -6.3065
Max Act: 6.3065. Min Act: -0.1700
Data Index: 419627 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3065. Min Range: -6.3065
Max Act: 6.2752. Min Act: -0.1700
Data Index: 2337030 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3065. Min Range: -6.3065
Max Act: 6.1502. Min Act: -0.1700
Data Index: 1078308 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3065. Min Range: -6.3065
Max Act: 6.1190. Min Act: -0.1700
Data Index: 4651218 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3065. Min Range: -6.3065
Max Act: 6.0877. Min Act: -0.1700
Data Index: 128953 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3065. Min Range: -6.3065
Max Act: 6.0252. Min Act: -0.1700
Data Index: 6902219 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3065. Min Range: -6.3065
Max Act: 6.0252. Min Act: -0.1700
Data Index: 7394010 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.9627. Min Act: -0.1700
Data Index: 5116960 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.9627. Min Act: -0.1700
Data Index: 1923993 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.9627. Min Act: -0.1700
Data Index: 5496543 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.9315. Min Act: -0.1700
Data Index: 7045 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.9002. Min Act: -0.1700
Data Index: 1519630 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.9315. Min Act: -0.1700
Data Index: 8617513 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.9002. Min Act: -0.1700
Data Index: 4145690 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.9002. Min Act: -0.1700
Data Index: 1053416 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.8690. Min Act: -0.1700
Data Index: 7711349 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.8690. Min Act: -0.1700
Data Index: 8779802 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.8690. Min Act: -0.1700
Data Index: 1393419 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3065. Min Range: -6.3065
Max Act: 5.8690. Min Act: -0.1700
Data Index: 5713669 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19