Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6146 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0709. Min Range: -5.0709
Max Act: 5.0709. Min Act: -0.1700
Data Index: 72357 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0709. Min Range: -5.0709
Max Act: 5.0709. Min Act: -0.1700
Data Index: 8495934 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0709. Min Range: -5.0709
Max Act: 5.0709. Min Act: -0.1700
Data Index: 802352 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0709. Min Range: -5.0709
Max Act: 5.0084. Min Act: -0.1700
Data Index: 7604289 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.9771. Min Act: -0.1700
Data Index: 4848431 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.9459. Min Act: -0.1700
Data Index: 8151664 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.9146. Min Act: -0.1700
Data Index: 1610114 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.8521. Min Act: -0.1700
Data Index: 6605286 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.7584. Min Act: -0.1700
Data Index: 5207631 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.7584. Min Act: -0.1700
Data Index: 1357008 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.7584. Min Act: -0.1700
Data Index: 1717715 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.7271. Min Act: -0.1700
Data Index: 2858528 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.7584. Min Act: -0.1700
Data Index: 5717985 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.7271. Min Act: -0.1699
Data Index: 4008836 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.7271. Min Act: -0.1700
Data Index: 8558276 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.7271. Min Act: -0.1700
Data Index: 798405 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.7271. Min Act: -0.1700
Data Index: 817219 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.7271. Min Act: -0.1700
Data Index: 3488272 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.6959. Min Act: -0.1700
Data Index: 2952527 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0709. Min Range: -5.0709
Max Act: 4.6959. Min Act: -0.1700
Data Index: 3217128 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19