Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3210 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.6298. Min Act: -0.1700
Data Index: 7113220 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.3173. Min Act: -0.1700
Data Index: 8543144 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.3173. Min Act: -0.1700
Data Index: 4072764 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.2548. Min Act: -0.1700
Data Index: 6450426 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.2548. Min Act: -0.1700
Data Index: 2901971 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.2548. Min Act: -0.1700
Data Index: 7390040 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.2235. Min Act: -0.1700
Data Index: 8211118 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.2235. Min Act: -0.1700
Data Index: 2610409 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.2235. Min Act: -0.1700
Data Index: 1726568 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1922. Min Act: -0.1700
Data Index: 7427120 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1922. Min Act: -0.1700
Data Index: 317356 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1610. Min Act: -0.1700
Data Index: 625364 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1297. Min Act: -0.1700
Data Index: 6598613 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1610. Min Act: -0.1700
Data Index: 8744012 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1610. Min Act: -0.1700
Data Index: 133649 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1610. Min Act: -0.1700
Data Index: 7205191 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1297. Min Act: -0.1700
Data Index: 3578963 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1297. Min Act: -0.1700
Data Index: 6805635 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1297. Min Act: -0.1700
Data Index: 4946316 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6298. Min Range: -4.6298
Max Act: 4.1297. Min Act: -0.1700
Data Index: 6991345 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19