Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4099 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.3488. Min Act: -0.1700
Data Index: 243151 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.2389. Min Act: -0.1700
Data Index: 1534705 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.1445. Min Act: -0.1700
Data Index: 7386102 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.1287. Min Act: -0.1700
Data Index: 6147606 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0657. Min Act: -0.1700
Data Index: 3143319 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0657. Min Act: -0.1700
Data Index: 7220170 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0657. Min Act: -0.1700
Data Index: 1692504 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0657. Min Act: -0.1700
Data Index: 55494 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0815. Min Act: -0.1700
Data Index: 1059410 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0341. Min Act: -0.1700
Data Index: 3268500 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0341. Min Act: -0.1700
Data Index: 8091681 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0183. Min Act: -0.1700
Data Index: 7814943 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0183. Min Act: -0.1700
Data Index: 779047 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0025. Min Act: -0.1700
Data Index: 4365113 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0025. Min Act: -0.1700
Data Index: 2223644 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3488. Min Range: -3.3488
Max Act: 3.0025. Min Act: -0.1700
Data Index: 3698535 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3488. Min Range: -3.3488
Max Act: 2.9709. Min Act: -0.1700
Data Index: 1604442 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3488. Min Range: -3.3488
Max Act: 2.9709. Min Act: -0.1700
Data Index: 7292730 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3488. Min Range: -3.3488
Max Act: 2.9551. Min Act: -0.1700
Data Index: 7855166 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3488. Min Range: -3.3488
Max Act: 2.9551. Min Act: -0.1700
Data Index: 5064176 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19