Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3488 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.9010. Min Act: -0.1700
Data Index: 8583512 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.9010. Min Act: -0.1700
Data Index: 7980441 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.8385. Min Act: -0.1680
Data Index: 3071715 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.7447. Min Act: -0.1699
Data Index: 7804316 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.7135. Min Act: -0.1700
Data Index: 5487563 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.7135. Min Act: -0.1698
Data Index: 2557600 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.6822. Min Act: -0.1700
Data Index: 7888950 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.6510. Min Act: -0.0615
Data Index: 6700880 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.6197. Min Act: -0.1696
Data Index: 972405 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.5885. Min Act: -0.1689
Data Index: 5478281 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.5885. Min Act: -0.1700
Data Index: 8680254 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.5885. Min Act: -0.1602
Data Index: 3490439 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.5885. Min Act: -0.1700
Data Index: 4896541 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.5572. Min Act: -0.1700
Data Index: 2806548 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.5260. Min Act: -0.1694
Data Index: 7267364 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.5572. Min Act: -0.1700
Data Index: 6589928 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.5260. Min Act: -0.1700
Data Index: 4025892 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.5260. Min Act: -0.1700
Data Index: 8053903 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.4947. Min Act: -0.1699
Data Index: 2588715 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9010. Min Range: -6.9010
Max Act: 6.4947. Min Act: -0.1700
Data Index: 2806546 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #19