Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.3514. Min Act: -0.1434
Data Index: 4047646 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.3514. Min Act: -0.1412
Data Index: 3319725 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.3337. Min Act: -0.1116
Data Index: 5416887 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.3161. Min Act: -0.1681
Data Index: 7608629 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.3161. Min Act: -0.1700
Data Index: 7100980 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.3073. Min Act: -0.1318
Data Index: 3594547 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.3161. Min Act: -0.1447
Data Index: 4111515 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.3073. Min Act: -0.1473
Data Index: 4047647 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.3073. Min Act: -0.1492
Data Index: 5421954 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2984. Min Act: -0.1461
Data Index: 5017009 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2896. Min Act: -0.1671
Data Index: 7732159 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2984. Min Act: -0.1553
Data Index: 7450326 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2896. Min Act: -0.1598
Data Index: 7909125 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2984. Min Act: -0.1602
Data Index: 6180817 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2896. Min Act: -0.1695
Data Index: 780289 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2896. Min Act: -0.1553
Data Index: 2518438 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2808. Min Act: -0.1585
Data Index: 1814016 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2896. Min Act: -0.1614
Data Index: 2085093 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2896. Min Act: -0.1594
Data Index: 4975355 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3514. Min Range: -1.3514
Max Act: 1.2896. Min Act: -0.1515
Data Index: 5742012 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19