Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 711 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.6752. Min Act: -0.1700
Data Index: 8003457 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.3002. Min Act: -0.1700
Data Index: 8225299 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.2690. Min Act: -0.1700
Data Index: 8382840 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.2377. Min Act: -0.1700
Data Index: 7094967 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1752. Min Act: -0.1700
Data Index: 7178471 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1752. Min Act: -0.1700
Data Index: 2421928 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1752. Min Act: -0.1700
Data Index: 896475 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1440. Min Act: -0.1700
Data Index: 8349754 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1440. Min Act: -0.1700
Data Index: 4987483 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1440. Min Act: -0.1700
Data Index: 4690644 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1127. Min Act: -0.1700
Data Index: 2497766 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1127. Min Act: -0.1700
Data Index: 8459887 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1127. Min Act: -0.1700
Data Index: 4262722 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1127. Min Act: -0.1700
Data Index: 3566933 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.0814. Min Act: -0.1700
Data Index: 2312564 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1127. Min Act: -0.1700
Data Index: 4460313 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.0814. Min Act: -0.1700
Data Index: 7262066 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.0814. Min Act: -0.1700
Data Index: 5323517 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.1127. Min Act: -0.1700
Data Index: 1369474 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6752. Min Range: -4.6752
Max Act: 4.0814. Min Act: -0.1700
Data Index: 201001 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19