Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 849 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.4627. Min Act: -0.1700
Data Index: 1719446 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.4314. Min Act: -0.1700
Data Index: 2475383 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.3064. Min Act: -0.1700
Data Index: 5627072 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.3064. Min Act: -0.1700
Data Index: 8058179 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.2752. Min Act: -0.1700
Data Index: 3599745 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.2752. Min Act: -0.1700
Data Index: 5906405 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.2752. Min Act: -0.1700
Data Index: 1902298 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.2752. Min Act: -0.1700
Data Index: 3783223 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.2439. Min Act: -0.1700
Data Index: 6527311 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.2439. Min Act: -0.1700
Data Index: 3434464 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.2439. Min Act: -0.1700
Data Index: 1836052 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.2127. Min Act: -0.1700
Data Index: 8534179 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.1814. Min Act: -0.1700
Data Index: 1878465 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.1814. Min Act: -0.1700
Data Index: 8269434 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.1814. Min Act: -0.1700
Data Index: 5519354 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.1814. Min Act: -0.1700
Data Index: 5622863 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.1502. Min Act: -0.1700
Data Index: 4006172 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.1189. Min Act: -0.1700
Data Index: 8052383 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.1502. Min Act: -0.1700
Data Index: 2114960 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4627. Min Range: -5.4627
Max Act: 5.1502. Min Act: -0.1700
Data Index: 2422638 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19