Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1800 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.7311. Min Act: -0.1700
Data Index: 6223552 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.6999. Min Act: -0.1700
Data Index: 3927483 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.6374. Min Act: -0.1700
Data Index: 5903876 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.6061. Min Act: -0.1700
Data Index: 7455841 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.6061. Min Act: -0.1700
Data Index: 4197617 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.6061. Min Act: -0.1700
Data Index: 1668862 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.6061. Min Act: -0.1700
Data Index: 4130792 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.5436. Min Act: -0.1700
Data Index: 7991833 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.5749. Min Act: -0.1700
Data Index: 6858356 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.5124. Min Act: -0.1700
Data Index: 502624 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.5436. Min Act: -0.1700
Data Index: 4484488 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.5124. Min Act: -0.1700
Data Index: 4540923 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.4811. Min Act: -0.1700
Data Index: 4630596 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.4499. Min Act: -0.1700
Data Index: 2290997 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.4499. Min Act: -0.1700
Data Index: 770575 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.4499. Min Act: -0.1700
Data Index: 6645062 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.4499. Min Act: -0.1700
Data Index: 6862289 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.3874. Min Act: -0.1700
Data Index: 5130572 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.4186. Min Act: -0.1700
Data Index: 3345353 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7311. Min Range: -5.7311
Max Act: 5.4499. Min Act: -0.1700
Data Index: 1718220 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19