Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6347 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.9375. Min Act: -0.1700
Data Index: 8543212 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.8125. Min Act: -0.1700
Data Index: 1022010 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7655. Min Act: -0.1700
Data Index: 5436053 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.7186. Min Act: -0.1700
Data Index: 7831459 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.6873. Min Act: -0.1700
Data Index: 6765435 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.6717. Min Act: -0.1700
Data Index: 2364799 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.6560. Min Act: -0.1700
Data Index: 4421452 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.5935. Min Act: -0.1700
Data Index: 4468351 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.6091. Min Act: -0.1700
Data Index: 3545171 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.6091. Min Act: -0.1700
Data Index: 8460208 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.6091. Min Act: -0.1700
Data Index: 2030803 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.5935. Min Act: -0.1700
Data Index: 2266079 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.5778. Min Act: -0.1700
Data Index: 7646024 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.5935. Min Act: -0.1700
Data Index: 2382793 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.5621. Min Act: -0.1700
Data Index: 5185038 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.5621. Min Act: -0.1700
Data Index: 7450992 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.5465. Min Act: -0.1700
Data Index: 8166210 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.5308. Min Act: -0.1700
Data Index: 4824405 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.4995. Min Act: -0.1700
Data Index: 1907960 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9375. Min Range: -3.9375
Max Act: 3.5152. Min Act: -0.1700
Data Index: 6501258 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #19