Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 641 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.4598. Min Act: -0.1700
Data Index: 3549378 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.3035. Min Act: -0.1700
Data Index: 2421362 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.3035. Min Act: -0.1700
Data Index: 6562233 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.2723. Min Act: -0.1700
Data Index: 6593663 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.2410. Min Act: -0.1700
Data Index: 817968 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.2098. Min Act: -0.1700
Data Index: 1924405 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.2410. Min Act: -0.1700
Data Index: 1776246 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.1785. Min Act: -0.1700
Data Index: 866235 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.1473. Min Act: -0.1700
Data Index: 878099 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0848. Min Act: -0.1700
Data Index: 5087114 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0535. Min Act: -0.1700
Data Index: 3118092 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0535. Min Act: -0.1700
Data Index: 1720554 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0223. Min Act: -0.1700
Data Index: 7724190 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4598. Min Range: -5.4598
Max Act: 4.9910. Min Act: -0.1700
Data Index: 8045430 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4598. Min Range: -5.4598
Max Act: 5.0223. Min Act: -0.1700
Data Index: 3102748 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4598. Min Range: -5.4598
Max Act: 4.9910. Min Act: -0.1700
Data Index: 641481 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4598. Min Range: -5.4598
Max Act: 4.9598. Min Act: -0.1700
Data Index: 2023409 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4598. Min Range: -5.4598
Max Act: 4.9910. Min Act: -0.1700
Data Index: 1522353 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4598. Min Range: -5.4598
Max Act: 4.9910. Min Act: -0.1700
Data Index: 7957112 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4598. Min Range: -5.4598
Max Act: 4.9910. Min Act: -0.1700
Data Index: 6330212 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19