Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3830 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3096. Min Range: -6.3096
Max Act: 6.3096. Min Act: -0.1700
Data Index: 8483752 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.9346. Min Act: -0.1700
Data Index: 2879593 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.9034. Min Act: -0.1700
Data Index: 3879018 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.9034. Min Act: -0.1700
Data Index: 8409895 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.8409. Min Act: -0.1700
Data Index: 1383756 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.8096. Min Act: -0.1700
Data Index: 8371120 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.7784. Min Act: -0.1700
Data Index: 6183152 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.7784. Min Act: -0.1700
Data Index: 7506276 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.7784. Min Act: -0.1700
Data Index: 5062637 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.7471. Min Act: -0.1700
Data Index: 1591993 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.7471. Min Act: -0.1700
Data Index: 2874881 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.6846. Min Act: -0.1700
Data Index: 3267681 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.6846. Min Act: -0.1700
Data Index: 8533641 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.7159. Min Act: -0.1700
Data Index: 5358089 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.7159. Min Act: -0.1700
Data Index: 4289519 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.6846. Min Act: -0.1700
Data Index: 5904908 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.6846. Min Act: -0.1700
Data Index: 6357871 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.6846. Min Act: -0.1700
Data Index: 2650584 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.6846. Min Act: -0.1700
Data Index: 4343609 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3096. Min Range: -6.3096
Max Act: 5.6534. Min Act: -0.1700
Data Index: 8026386 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19