Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 828 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1388. Min Range: -3.1388
Max Act: 3.1388. Min Act: -0.1700
Data Index: 7990053 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9968. Min Act: -0.1700
Data Index: 2270610 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9810. Min Act: -0.1700
Data Index: 982907 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9335. Min Act: -0.1700
Data Index: 4923335 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9335. Min Act: -0.1700
Data Index: 4923350 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9177. Min Act: -0.1700
Data Index: 8079119 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9018. Min Act: -0.1700
Data Index: 7990054 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8701. Min Act: -0.1700
Data Index: 812224 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8701. Min Act: -0.1700
Data Index: 4026935 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8542. Min Act: -0.1700
Data Index: 4870881 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8542. Min Act: -0.1700
Data Index: 230457 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8542. Min Act: -0.1700
Data Index: 1384891 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8542. Min Act: -0.1700
Data Index: 5567720 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8542. Min Act: -0.1700
Data Index: 6035549 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8542. Min Act: -0.1700
Data Index: 3652533 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8542. Min Act: -0.1700
Data Index: 4923353 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8383. Min Act: -0.1700
Data Index: 5603453 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8383. Min Act: -0.1700
Data Index: 2935006 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8224. Min Act: -0.1700
Data Index: 959164 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8224. Min Act: -0.1700
Data Index: 4861784 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #19