Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0276. Min Range: -5.0276
Max Act: 5.0276. Min Act: -0.1700
Data Index: 849628 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.8713. Min Act: -0.1700
Data Index: 5025210 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.8088. Min Act: -0.1700
Data Index: 7911484 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.8401. Min Act: -0.1700
Data Index: 5690737 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.7463. Min Act: -0.1700
Data Index: 7293333 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.7463. Min Act: -0.1700
Data Index: 2018618 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.6838. Min Act: -0.1700
Data Index: 7324560 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.6838. Min Act: -0.1700
Data Index: 5730221 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.6526. Min Act: -0.1700
Data Index: 5408358 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.6526. Min Act: -0.1700
Data Index: 5488178 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.6526. Min Act: -0.1700
Data Index: 5799274 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.6526. Min Act: -0.1700
Data Index: 520562 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.6526. Min Act: -0.1700
Data Index: 4123981 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.5588. Min Act: -0.1700
Data Index: 6856829 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.5901. Min Act: -0.1700
Data Index: 2583895 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.5901. Min Act: -0.1700
Data Index: 6688546 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.5901. Min Act: -0.1700
Data Index: 2505962 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.6213. Min Act: -0.1700
Data Index: 2468291 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.5901. Min Act: -0.1700
Data Index: 1818985 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0276. Min Range: -5.0276
Max Act: 4.5901. Min Act: -0.1700
Data Index: 5876042 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19