Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2658 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.1694. Min Range: -4.1694
Max Act: 4.1694. Min Act: -0.1700
Data Index: 4892436 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.8725. Min Act: -0.1700
Data Index: 4464522 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.8412. Min Act: -0.1700
Data Index: 5313182 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.8256. Min Act: -0.1700
Data Index: 5515298 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7943. Min Act: -0.1700
Data Index: 2203982 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.8099. Min Act: -0.1700
Data Index: 6826008 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.8099. Min Act: -0.1700
Data Index: 4954626 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7786. Min Act: -0.1700
Data Index: 4712101 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7630. Min Act: -0.1700
Data Index: 1494874 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7786. Min Act: -0.1700
Data Index: 1952669 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7786. Min Act: -0.1700
Data Index: 4708439 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7317. Min Act: -0.1700
Data Index: 4830087 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7317. Min Act: -0.1700
Data Index: 1991129 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7004. Min Act: -0.1700
Data Index: 4042500 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7161. Min Act: -0.1700
Data Index: 1994501 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7161. Min Act: -0.1700
Data Index: 8553549 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7004. Min Act: -0.1700
Data Index: 2082414 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7004. Min Act: -0.1700
Data Index: 575460 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.7161. Min Act: -0.1700
Data Index: 8573412 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1694. Min Range: -4.1694
Max Act: 3.6692. Min Act: -0.1700
Data Index: 6302332 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19