Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3812 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.6412. Min Act: -0.1700
Data Index: 7753807 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.5787. Min Act: -0.1700
Data Index: 1240897 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.5474. Min Act: -0.1700
Data Index: 7838997 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.5787. Min Act: -0.1700
Data Index: 732416 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.5162. Min Act: -0.1700
Data Index: 3543626 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.4224. Min Act: -0.1700
Data Index: 1878587 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.4537. Min Act: -0.1700
Data Index: 7419283 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.4224. Min Act: -0.1700
Data Index: 6312754 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.4537. Min Act: -0.1700
Data Index: 8777442 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.4224. Min Act: -0.1700
Data Index: 8520587 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.4224. Min Act: -0.1700
Data Index: 6153775 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.4224. Min Act: -0.1700
Data Index: 1983744 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.3599. Min Act: -0.1700
Data Index: 1635363 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.3912. Min Act: -0.1700
Data Index: 4638119 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.3912. Min Act: -0.1700
Data Index: 408259 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.3599. Min Act: -0.1700
Data Index: 4151622 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.3599. Min Act: -0.1700
Data Index: 3803880 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.3599. Min Act: -0.1700
Data Index: 8707109 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.3287. Min Act: -0.1700
Data Index: 7465508 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6412. Min Range: -5.6412
Max Act: 5.3287. Min Act: -0.1700
Data Index: 3017862 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19