Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2231. Min Range: -4.2231
Max Act: 4.2231. Min Act: -0.1700
Data Index: 3354518 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2231. Min Range: -4.2231
Max Act: 4.0356. Min Act: -0.1700
Data Index: 2404766 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.9730. Min Act: -0.1700
Data Index: 3030164 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2231. Min Range: -4.2231
Max Act: 4.0043. Min Act: -0.1700
Data Index: 4218044 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.9418. Min Act: -0.1700
Data Index: 42258 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.9105. Min Act: -0.1700
Data Index: 6686256 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.9105. Min Act: -0.1700
Data Index: 47964 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.9261. Min Act: -0.1700
Data Index: 4954506 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.9105. Min Act: -0.1700
Data Index: 4954516 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.8949. Min Act: -0.1700
Data Index: 5590715 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.8480. Min Act: -0.1700
Data Index: 8806880 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.8636. Min Act: -0.1700
Data Index: 8806877 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.8011. Min Act: -0.1700
Data Index: 1354155 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.8323. Min Act: -0.1700
Data Index: 7749606 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.7542. Min Act: -0.1700
Data Index: 7320 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.7854. Min Act: -0.1700
Data Index: 62441 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.8323. Min Act: -0.1700
Data Index: 3779893 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.7542. Min Act: -0.1700
Data Index: 5365658 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.7854. Min Act: -0.1700
Data Index: 6557805 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2231. Min Range: -4.2231
Max Act: 3.7854. Min Act: -0.1700
Data Index: 8333145 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19