Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3286 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0277. Min Range: -6.0277
Max Act: 6.0277. Min Act: -0.1700
Data Index: 6618748 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8715. Min Act: -0.1700
Data Index: 8251443 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8715. Min Act: -0.1700
Data Index: 6165572 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8715. Min Act: -0.1700
Data Index: 575713 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8715. Min Act: -0.1700
Data Index: 7195658 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8402. Min Act: -0.1700
Data Index: 1408797 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8402. Min Act: -0.1700
Data Index: 4840960 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8715. Min Act: -0.1700
Data Index: 1437780 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8402. Min Act: -0.1700
Data Index: 8490951 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8402. Min Act: -0.1700
Data Index: 1132648 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8402. Min Act: -0.1700
Data Index: 2406234 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8402. Min Act: -0.1700
Data Index: 723178 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8402. Min Act: -0.1700
Data Index: 7981745 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8090. Min Act: -0.1699
Data Index: 8181354 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8090. Min Act: -0.1700
Data Index: 2043933 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8090. Min Act: -0.1700
Data Index: 7222258 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8090. Min Act: -0.1700
Data Index: 5630228 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.8090. Min Act: -0.1700
Data Index: 8084423 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.7777. Min Act: -0.1700
Data Index: 5512138 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0277. Min Range: -6.0277
Max Act: 5.7777. Min Act: -0.1700
Data Index: 7192391 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19