Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2623 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.6652. Min Act: -0.1700
Data Index: 5212193 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.6652. Min Act: -0.1700
Data Index: 597117 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.6339. Min Act: -0.1700
Data Index: 4331729 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.6027. Min Act: -0.1700
Data Index: 7917406 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.6027. Min Act: -0.1700
Data Index: 5987177 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.5089. Min Act: -0.1700
Data Index: 692246 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.5089. Min Act: -0.1700
Data Index: 7327341 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.5089. Min Act: -0.1700
Data Index: 8151307 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.5089. Min Act: -0.1700
Data Index: 7297691 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.5089. Min Act: -0.1700
Data Index: 3378097 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.4777. Min Act: -0.1700
Data Index: 2125954 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.4777. Min Act: -0.1700
Data Index: 2890377 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.4777. Min Act: -0.1700
Data Index: 8791885 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.4464. Min Act: -0.1700
Data Index: 8657505 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.4152. Min Act: -0.1700
Data Index: 7841858 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.4152. Min Act: -0.1700
Data Index: 3663485 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.3839. Min Act: -0.1700
Data Index: 7100003 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.3839. Min Act: -0.1700
Data Index: 3563302 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.3839. Min Act: -0.1700
Data Index: 5832860 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6652. Min Range: -5.6652
Max Act: 5.3839. Min Act: -0.1700
Data Index: 1541607 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19