Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4518 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.5096. Min Act: -0.1700
Data Index: 7749680 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.4158. Min Act: -0.1700
Data Index: 1346120 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.4158. Min Act: -0.1700
Data Index: 894689 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.2596. Min Act: -0.1700
Data Index: 7139221 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.1971. Min Act: -0.1700
Data Index: 2710613 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.1658. Min Act: -0.1700
Data Index: 7680508 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0721. Min Act: -0.1700
Data Index: 5476512 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0721. Min Act: -0.1700
Data Index: 4704207 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0408. Min Act: -0.1700
Data Index: 2580675 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0721. Min Act: -0.1700
Data Index: 1371782 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0721. Min Act: -0.1700
Data Index: 1953638 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0721. Min Act: -0.1700
Data Index: 7460461 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0408. Min Act: -0.1700
Data Index: 744005 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0408. Min Act: -0.1700
Data Index: 668155 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0096. Min Act: -0.1700
Data Index: 4801103 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0096. Min Act: -0.1700
Data Index: 4486907 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5096. Min Range: -5.5096
Max Act: 4.9783. Min Act: -0.1700
Data Index: 5218292 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5096. Min Range: -5.5096
Max Act: 4.9783. Min Act: -0.1700
Data Index: 770100 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5096. Min Range: -5.5096
Max Act: 4.9471. Min Act: -0.1700
Data Index: 362806 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5096. Min Range: -5.5096
Max Act: 5.0096. Min Act: -0.1700
Data Index: 190794 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19