Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2589 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.9666. Min Act: -0.1554
Data Index: 3733102 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.9411. Min Act: -0.1696
Data Index: 1077482 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.9156. Min Act: -0.1591
Data Index: 8778637 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8730. Min Act: -0.1698
Data Index: 6034639 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8473. Min Act: -0.1559
Data Index: 6272111 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8473. Min Act: -0.1582
Data Index: 1941768 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8387. Min Act: -0.1645
Data Index: 822115 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8302. Min Act: -0.1586
Data Index: 4396608 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8216. Min Act: -0.1685
Data Index: 4509023 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8216. Min Act: -0.1512
Data Index: 4509024 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8216. Min Act: -0.1549
Data Index: 8481544 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8130. Min Act: -0.1512
Data Index: 4509025 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8130. Min Act: -0.1680
Data Index: 4509026 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8044. Min Act: -0.1690
Data Index: 1077483 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.8044. Min Act: -0.1512
Data Index: 4509027 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.7958. Min Act: -0.1632
Data Index: 4704974 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.7872. Min Act: -0.1512
Data Index: 1887827 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.7786. Min Act: -0.1674
Data Index: 1077484 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.7613. Min Act: -0.1512
Data Index: 8236645 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9666. Min Range: -1.9666
Max Act: 1.7613. Min Act: -0.1559
Data Index: 2801833 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19