Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.8627. Min Act: -0.1700
Data Index: 589369 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.8315. Min Act: -0.1700
Data Index: 4602903 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.8315. Min Act: -0.1700
Data Index: 1656633 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.8002. Min Act: -0.1700
Data Index: 7650640 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.8002. Min Act: -0.1700
Data Index: 1401603 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7690. Min Act: -0.1700
Data Index: 5641402 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7377. Min Act: -0.1700
Data Index: 8138508 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7690. Min Act: -0.1700
Data Index: 7650638 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7377. Min Act: -0.1700
Data Index: 8448699 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7377. Min Act: -0.1700
Data Index: 1224358 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7065. Min Act: -0.1700
Data Index: 7407196 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.6752. Min Act: -0.1700
Data Index: 8024310 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7065. Min Act: -0.1700
Data Index: 8640111 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.6752. Min Act: -0.1700
Data Index: 1583656 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7065. Min Act: -0.1700
Data Index: 4796913 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7065. Min Act: -0.1700
Data Index: 3708016 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7065. Min Act: -0.1700
Data Index: 7480363 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.7065. Min Act: -0.1700
Data Index: 4145021 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.6752. Min Act: -0.1700
Data Index: 878638 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8627. Min Range: -4.8627
Max Act: 4.6752. Min Act: -0.1700
Data Index: 2110477 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19