Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1379 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.7940. Min Act: -0.1700
Data Index: 637045 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.7002. Min Act: -0.1700
Data Index: 10529 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.6690. Min Act: -0.1700
Data Index: 1875386 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.6690. Min Act: -0.1700
Data Index: 943667 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.6377. Min Act: -0.1700
Data Index: 2019888 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.5752. Min Act: -0.1700
Data Index: 7304547 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.5752. Min Act: -0.1700
Data Index: 7875887 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.5752. Min Act: -0.1700
Data Index: 7773154 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.5752. Min Act: -0.1700
Data Index: 793837 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.5440. Min Act: -0.1700
Data Index: 7699992 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.5127. Min Act: -0.1700
Data Index: 5256525 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.5127. Min Act: -0.1700
Data Index: 1892103 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.5127. Min Act: -0.1700
Data Index: 4869200 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.5127. Min Act: -0.1700
Data Index: 8324992 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.5127. Min Act: -0.1700
Data Index: 6520517 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.4815. Min Act: -0.1700
Data Index: 5356866 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.4815. Min Act: -0.1700
Data Index: 8487999 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.4815. Min Act: -0.1700
Data Index: 3745213 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.4815. Min Act: -0.1700
Data Index: 7396661 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7940. Min Range: -4.7940
Max Act: 4.4502. Min Act: -0.1700
Data Index: 2550070 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19