Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 537 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.6508. Min Act: -0.1700
Data Index: 2885320 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.4934. Min Act: -0.1690
Data Index: 371726 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.4231. Min Act: -0.1698
Data Index: 8132960 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.4055. Min Act: -0.1698
Data Index: 4656747 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.4231. Min Act: -0.1700
Data Index: 8131368 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.4231. Min Act: -0.1675
Data Index: 5708656 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3878. Min Act: -0.1696
Data Index: 2492843 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3878. Min Act: -0.1698
Data Index: 903921 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.4055. Min Act: -0.1686
Data Index: 5976498 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.4407. Min Act: -0.1700
Data Index: 3993970 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3878. Min Act: -0.1696
Data Index: 1693644 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3526. Min Act: -0.1674
Data Index: 438955 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3702. Min Act: -0.1700
Data Index: 3546237 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3702. Min Act: -0.1575
Data Index: 3567177 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3702. Min Act: -0.1685
Data Index: 2292053 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3526. Min Act: -0.1694
Data Index: 7480873 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3526. Min Act: -0.1699
Data Index: 6500341 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3349. Min Act: -0.1700
Data Index: 2119490 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3526. Min Act: -0.1691
Data Index: 3944908 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6508. Min Range: -1.6508
Max Act: 1.3173. Min Act: -0.1575
Data Index: 5733336 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #19