Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2570 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.3896. Min Act: -0.1700
Data Index: 148701 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.3896. Min Act: -0.1700
Data Index: 6298324 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.2021. Min Act: -0.1700
Data Index: 1695094 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.2646. Min Act: -0.1700
Data Index: 7278084 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.2021. Min Act: -0.1700
Data Index: 7963976 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.2021. Min Act: -0.1700
Data Index: 2261568 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.1396. Min Act: -0.1700
Data Index: 2010936 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.0146. Min Act: -0.1700
Data Index: 8711605 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.0771. Min Act: -0.1700
Data Index: 3866521 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.0771. Min Act: -0.1700
Data Index: 1204765 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.0771. Min Act: -0.1700
Data Index: 2221366 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.0771. Min Act: -0.1700
Data Index: 7963973 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.0146. Min Act: -0.1700
Data Index: 8587019 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.0146. Min Act: -0.1700
Data Index: 4630743 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3896. Min Range: -9.3896
Max Act: 9.0146. Min Act: -0.1700
Data Index: 6492465 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3896. Min Range: -9.3896
Max Act: 8.9521. Min Act: -0.1700
Data Index: 6661918 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3896. Min Range: -9.3896
Max Act: 8.9521. Min Act: -0.1700
Data Index: 5876897 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3896. Min Range: -9.3896
Max Act: 8.9521. Min Act: -0.1700
Data Index: 8543380 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3896. Min Range: -9.3896
Max Act: 8.9521. Min Act: -0.1700
Data Index: 8797862 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3896. Min Range: -9.3896
Max Act: 8.8896. Min Act: -0.1700
Data Index: 6563792 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19