Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3644 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1158. Min Range: -5.1158
Max Act: 5.1158. Min Act: -0.1700
Data Index: 1380087 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1158. Min Range: -5.1158
Max Act: 5.0533. Min Act: -0.1700
Data Index: 4034177 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1158. Min Range: -5.1158
Max Act: 5.0221. Min Act: -0.1700
Data Index: 4395398 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1158. Min Range: -5.1158
Max Act: 5.0221. Min Act: -0.1700
Data Index: 6959917 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.9908. Min Act: -0.1700
Data Index: 6816744 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.9596. Min Act: -0.1700
Data Index: 1650559 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.9283. Min Act: -0.1700
Data Index: 8830011 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8971. Min Act: -0.1700
Data Index: 6783702 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8971. Min Act: -0.1700
Data Index: 4838019 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8971. Min Act: -0.1700
Data Index: 4974792 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8658. Min Act: -0.1700
Data Index: 4779629 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8658. Min Act: -0.1700
Data Index: 4099325 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8971. Min Act: -0.1700
Data Index: 609403 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8658. Min Act: -0.1700
Data Index: 8405924 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8658. Min Act: -0.1700
Data Index: 142067 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8658. Min Act: -0.1700
Data Index: 3706239 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8346. Min Act: -0.1700
Data Index: 3894594 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8346. Min Act: -0.1700
Data Index: 163882 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8346. Min Act: -0.1700
Data Index: 1085183 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8346. Min Act: -0.1700
Data Index: 1116704 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19