Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2447 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1232. Min Range: -3.1232
Max Act: 3.1232. Min Act: -0.1700
Data Index: 2089439 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9970. Min Act: -0.1700
Data Index: 1837813 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1232. Min Range: -3.1232
Max Act: 3.0128. Min Act: -0.1700
Data Index: 7847409 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1232. Min Range: -3.1232
Max Act: 3.0128. Min Act: -0.1700
Data Index: 421320 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9970. Min Act: -0.1700
Data Index: 3324162 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9812. Min Act: -0.1700
Data Index: 8334474 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9970. Min Act: -0.1700
Data Index: 8466794 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9812. Min Act: -0.1700
Data Index: 7062694 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9812. Min Act: -0.1700
Data Index: 5862926 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9654. Min Act: -0.1700
Data Index: 3867424 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9970. Min Act: -0.1700
Data Index: 6881689 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9496. Min Act: -0.1700
Data Index: 8727338 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9337. Min Act: -0.1700
Data Index: 7623238 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9337. Min Act: -0.1700
Data Index: 347100 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9020. Min Act: -0.1700
Data Index: 3765968 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9179. Min Act: -0.1700
Data Index: 7133179 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9179. Min Act: -0.1700
Data Index: 29559 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9179. Min Act: -0.1700
Data Index: 4773067 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9020. Min Act: -0.1700
Data Index: 1358545 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1232. Min Range: -3.1232
Max Act: 2.9179. Min Act: -0.1700
Data Index: 4644103 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19