Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 556 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.5645. Min Act: -0.1700
Data Index: 1117834 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.5333. Min Act: -0.1700
Data Index: 4726265 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.5020. Min Act: -0.1700
Data Index: 4934465 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.2208. Min Act: -0.1700
Data Index: 4416432 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.2208. Min Act: -0.1700
Data Index: 2164385 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.1895. Min Act: -0.1700
Data Index: 2019552 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.1582. Min Act: -0.1700
Data Index: 1360840 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.1582. Min Act: -0.1700
Data Index: 2527221 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.1270. Min Act: -0.1700
Data Index: 1394661 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.0957. Min Act: -0.1700
Data Index: 2171271 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.1270. Min Act: -0.1700
Data Index: 7572445 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.0957. Min Act: -0.1700
Data Index: 7288923 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.0957. Min Act: -0.1700
Data Index: 7189989 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.0957. Min Act: -0.1700
Data Index: 5436261 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.0645. Min Act: -0.1700
Data Index: 7322545 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.0645. Min Act: -0.1700
Data Index: 4028236 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.0645. Min Act: -0.1700
Data Index: 5047472 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.0332. Min Act: -0.1700
Data Index: 4555274 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.0332. Min Act: -0.1700
Data Index: 4145308 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5645. Min Range: -4.5645
Max Act: 4.0332. Min Act: -0.1700
Data Index: 1771441 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19