Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2736 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.7162. Min Act: -0.1700
Data Index: 6927970 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.6850. Min Act: -0.1700
Data Index: 2567902 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.5287. Min Act: -0.1700
Data Index: 8020766 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.5287. Min Act: -0.1700
Data Index: 8604242 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.5287. Min Act: -0.1700
Data Index: 4551718 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.5287. Min Act: -0.1700
Data Index: 1740588 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.5600. Min Act: -0.1700
Data Index: 4302817 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.5600. Min Act: -0.1700
Data Index: 1335343 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4662. Min Act: -0.1700
Data Index: 442373 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4975. Min Act: -0.1700
Data Index: 6196156 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4662. Min Act: -0.1700
Data Index: 2174640 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4350. Min Act: -0.1700
Data Index: 5689220 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4037. Min Act: -0.1700
Data Index: 7217174 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4037. Min Act: -0.1700
Data Index: 1136735 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4037. Min Act: -0.1700
Data Index: 3951976 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4037. Min Act: -0.1700
Data Index: 8762290 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4350. Min Act: -0.1700
Data Index: 4522454 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4037. Min Act: -0.1700
Data Index: 4017536 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4037. Min Act: -0.1700
Data Index: 5463457 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7162. Min Range: -5.7162
Max Act: 5.4037. Min Act: -0.1700
Data Index: 3474776 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19