Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 572 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1673. Min Range: -5.1673
Max Act: 5.1673. Min Act: -0.1700
Data Index: 6506714 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.9173. Min Act: -0.1700
Data Index: 6101195 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.8548. Min Act: -0.1700
Data Index: 170056 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.8548. Min Act: -0.1700
Data Index: 7572144 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.8548. Min Act: -0.1700
Data Index: 8634076 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.8235. Min Act: -0.1700
Data Index: 6495733 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.7923. Min Act: -0.1700
Data Index: 521162 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.7610. Min Act: -0.1700
Data Index: 8047667 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.7610. Min Act: -0.1700
Data Index: 8096241 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.7298. Min Act: -0.1700
Data Index: 2161821 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.7298. Min Act: -0.1700
Data Index: 7102633 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.6985. Min Act: -0.1700
Data Index: 2539306 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.6673. Min Act: -0.1700
Data Index: 7460521 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.6985. Min Act: -0.1700
Data Index: 7856399 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.6985. Min Act: -0.1700
Data Index: 275383 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.6673. Min Act: -0.1700
Data Index: 3769001 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.6985. Min Act: -0.1700
Data Index: 7699360 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.6673. Min Act: -0.1700
Data Index: 3452926 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.6673. Min Act: -0.1700
Data Index: 3619800 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.6360. Min Act: -0.1700
Data Index: 7755253 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19