Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 384 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5099. Min Range: -5.5099
Max Act: 5.5099. Min Act: -0.1700
Data Index: 4787190 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5099. Min Range: -5.5099
Max Act: 5.2286. Min Act: -0.1700
Data Index: 3755069 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5099. Min Range: -5.5099
Max Act: 5.2599. Min Act: -0.1700
Data Index: 7002375 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5099. Min Range: -5.5099
Max Act: 5.2599. Min Act: -0.1700
Data Index: 1915726 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5099. Min Range: -5.5099
Max Act: 5.1349. Min Act: -0.1700
Data Index: 3153337 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5099. Min Range: -5.5099
Max Act: 5.0099. Min Act: -0.1700
Data Index: 3214103 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.9474. Min Act: -0.1700
Data Index: 7954626 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.9474. Min Act: -0.1700
Data Index: 3303257 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.9474. Min Act: -0.1700
Data Index: 4289403 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.9161. Min Act: -0.1700
Data Index: 6150685 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.8849. Min Act: -0.1700
Data Index: 7852569 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.8536. Min Act: -0.1700
Data Index: 7852595 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.8536. Min Act: -0.1700
Data Index: 3423756 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.8536. Min Act: -0.1700
Data Index: 8013973 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.8536. Min Act: -0.1700
Data Index: 5435929 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.8224. Min Act: -0.1700
Data Index: 7032481 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.7911. Min Act: -0.1700
Data Index: 3595978 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.7911. Min Act: -0.1700
Data Index: 7695382 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.7911. Min Act: -0.1700
Data Index: 6434112 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5099. Min Range: -5.5099
Max Act: 4.7599. Min Act: -0.1700
Data Index: 3245297 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19