Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1609 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.4793. Min Act: -0.1700
Data Index: 3936802 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.3855. Min Act: -0.1700
Data Index: 3405380 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.3855. Min Act: -0.1700
Data Index: 2606065 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.3543. Min Act: -0.1700
Data Index: 2433772 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.3230. Min Act: -0.1700
Data Index: 6224721 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1980. Min Act: -0.1700
Data Index: 1485155 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.2293. Min Act: -0.1700
Data Index: 257351 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1667. Min Act: -0.1700
Data Index: 521498 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1667. Min Act: -0.1700
Data Index: 674284 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1980. Min Act: -0.1700
Data Index: 4715933 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1667. Min Act: -0.1700
Data Index: 8414770 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1667. Min Act: -0.1700
Data Index: 4138679 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1042. Min Act: -0.1700
Data Index: 222941 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1355. Min Act: -0.1700
Data Index: 1056706 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1355. Min Act: -0.1700
Data Index: 2202829 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1042. Min Act: -0.1700
Data Index: 6224716 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.0730. Min Act: -0.1700
Data Index: 3465764 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1355. Min Act: -0.1700
Data Index: 8414769 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.1042. Min Act: -0.1700
Data Index: 1056714 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4793. Min Range: -4.4793
Max Act: 4.0730. Min Act: -0.1700
Data Index: 2955932 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19