Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2547. Min Range: -8.2547
Max Act: 8.2547. Min Act: -0.1700
Data Index: 6766033 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2547. Min Range: -8.2547
Max Act: 8.1922. Min Act: -0.1700
Data Index: 90305 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.9422. Min Act: -0.1700
Data Index: 2932089 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.6610. Min Act: -0.1700
Data Index: 2689487 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.6610. Min Act: -0.1700
Data Index: 7415508 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.5985. Min Act: -0.1700
Data Index: 4373016 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.5985. Min Act: -0.1700
Data Index: 4685049 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.5360. Min Act: -0.1700
Data Index: 6253701 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.5360. Min Act: -0.1700
Data Index: 7569335 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.4735. Min Act: -0.1700
Data Index: 8060973 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.4422. Min Act: -0.1700
Data Index: 1975561 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.4110. Min Act: -0.1700
Data Index: 6996016 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.3797. Min Act: -0.1700
Data Index: 3993330 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.3797. Min Act: -0.1700
Data Index: 5471808 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.3172. Min Act: -0.1700
Data Index: 4290798 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.3172. Min Act: -0.1700
Data Index: 462471 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.3172. Min Act: -0.1700
Data Index: 4388979 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.2860. Min Act: -0.1700
Data Index: 2149778 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.2860. Min Act: -0.1700
Data Index: 1359326 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2547. Min Range: -8.2547
Max Act: 7.2860. Min Act: -0.1700
Data Index: 2109421 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19