Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5771 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.8096. Min Act: -0.1700
Data Index: 967291 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.7471. Min Act: -0.1700
Data Index: 6388983 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.7471. Min Act: -0.1700
Data Index: 4140580 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.7158. Min Act: -0.1700
Data Index: 5654397 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.7158. Min Act: -0.1700
Data Index: 8761286 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.6533. Min Act: -0.1700
Data Index: 5148805 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.6533. Min Act: -0.1700
Data Index: 3416512 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5908. Min Act: -0.1700
Data Index: 3438001 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5908. Min Act: -0.1700
Data Index: 3258068 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5908. Min Act: -0.1700
Data Index: 4031115 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5596. Min Act: -0.1700
Data Index: 3258065 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5908. Min Act: -0.1700
Data Index: 4127600 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5596. Min Act: -0.1700
Data Index: 6937912 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5596. Min Act: -0.1700
Data Index: 3129077 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5908. Min Act: -0.1700
Data Index: 5488773 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5596. Min Act: -0.1700
Data Index: 1310502 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5596. Min Act: -0.1700
Data Index: 6937916 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5596. Min Act: -0.1700
Data Index: 4581602 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5596. Min Act: -0.1700
Data Index: 397704 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8096. Min Range: -5.8096
Max Act: 5.5596. Min Act: -0.1700
Data Index: 2393007 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19