Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.3905. Min Act: -0.1700
Data Index: 6518397 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.3593. Min Act: -0.1700
Data Index: 6009351 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.3280. Min Act: -0.1700
Data Index: 5441842 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2968. Min Act: -0.1700
Data Index: 3559586 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.3280. Min Act: -0.1700
Data Index: 941771 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2968. Min Act: -0.1700
Data Index: 8471008 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2968. Min Act: -0.1700
Data Index: 5248287 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2968. Min Act: -0.1700
Data Index: 5204630 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2655. Min Act: -0.1700
Data Index: 1438811 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2655. Min Act: -0.1700
Data Index: 5003693 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2655. Min Act: -0.1700
Data Index: 3747132 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2343. Min Act: -0.1700
Data Index: 3222246 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2343. Min Act: -0.1700
Data Index: 5546167 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2343. Min Act: -0.1700
Data Index: 2283997 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2343. Min Act: -0.1700
Data Index: 2019299 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2655. Min Act: -0.1700
Data Index: 8265861 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2030. Min Act: -0.1700
Data Index: 4294262 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2343. Min Act: -0.1700
Data Index: 4792486 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2343. Min Act: -0.1700
Data Index: 6815640 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3905. Min Range: -4.3905
Max Act: 4.2030. Min Act: -0.1700
Data Index: 7876900 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #19