Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4783. Min Range: -6.4783
Max Act: 6.4783. Min Act: -0.1700
Data Index: 6572747 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4783. Min Range: -6.4783
Max Act: 6.2595. Min Act: -0.1700
Data Index: 7230222 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4783. Min Range: -6.4783
Max Act: 6.1345. Min Act: -0.1700
Data Index: 4028560 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4783. Min Range: -6.4783
Max Act: 6.1658. Min Act: -0.1700
Data Index: 6783744 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4783. Min Range: -6.4783
Max Act: 6.1033. Min Act: -0.1700
Data Index: 180535 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4783. Min Range: -6.4783
Max Act: 6.0408. Min Act: -0.1700
Data Index: 4396740 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4783. Min Range: -6.4783
Max Act: 6.0095. Min Act: -0.1700
Data Index: 6427863 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4783. Min Range: -6.4783
Max Act: 6.0095. Min Act: -0.1700
Data Index: 6711108 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.9470. Min Act: -0.1700
Data Index: 2251474 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.9783. Min Act: -0.1700
Data Index: 1583243 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.9158. Min Act: -0.1700
Data Index: 5442015 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.9158. Min Act: -0.1700
Data Index: 7288043 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.9158. Min Act: -0.1700
Data Index: 6286042 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.9158. Min Act: -0.1700
Data Index: 8032340 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.9158. Min Act: -0.1700
Data Index: 2541297 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.8845. Min Act: -0.1700
Data Index: 593647 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.8845. Min Act: -0.1700
Data Index: 5323623 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.9158. Min Act: -0.1700
Data Index: 5787454 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.9158. Min Act: -0.1700
Data Index: 42484 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4783. Min Range: -6.4783
Max Act: 5.8845. Min Act: -0.1700
Data Index: 6130895 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19