Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3017 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.7839. Min Act: -0.1700
Data Index: 3663937 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.5339. Min Act: -0.1700
Data Index: 7019636 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.4714. Min Act: -0.1700
Data Index: 2745987 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.3777. Min Act: -0.1700
Data Index: 6782935 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.3464. Min Act: -0.1700
Data Index: 5225516 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.3777. Min Act: -0.1700
Data Index: 2275669 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.3152. Min Act: -0.1700
Data Index: 301684 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.2839. Min Act: -0.1700
Data Index: 1119266 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.2839. Min Act: -0.1700
Data Index: 7616685 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.2214. Min Act: -0.1700
Data Index: 4182782 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.2214. Min Act: -0.1700
Data Index: 4304507 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.2214. Min Act: -0.1700
Data Index: 7481970 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.1589. Min Act: -0.1700
Data Index: 1894752 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.1902. Min Act: -0.1700
Data Index: 3658439 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.1589. Min Act: -0.1700
Data Index: 7280247 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.1589. Min Act: -0.1700
Data Index: 7023768 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.1277. Min Act: -0.1700
Data Index: 8259601 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.1277. Min Act: -0.1700
Data Index: 549865 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.1277. Min Act: -0.1700
Data Index: 7532293 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7839. Min Range: -5.7839
Max Act: 5.1277. Min Act: -0.1700
Data Index: 2493417 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19