Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1423 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.7550. Min Act: -0.1700
Data Index: 2967387 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.7238. Min Act: -0.1700
Data Index: 4029924 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.6613. Min Act: -0.1700
Data Index: 5325839 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.6613. Min Act: -0.1700
Data Index: 840703 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5675. Min Act: -0.1700
Data Index: 5599855 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5675. Min Act: -0.1700
Data Index: 912029 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.5050. Min Act: -0.1700
Data Index: 1729075 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4738. Min Act: -0.1700
Data Index: 3480941 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4738. Min Act: -0.1700
Data Index: 3721125 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4425. Min Act: -0.1700
Data Index: 4622942 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4113. Min Act: -0.1700
Data Index: 310449 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4425. Min Act: -0.1700
Data Index: 819808 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4113. Min Act: -0.1700
Data Index: 2692832 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4113. Min Act: -0.1700
Data Index: 5716467 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4113. Min Act: -0.1700
Data Index: 6576533 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.4113. Min Act: -0.1700
Data Index: 3367929 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.3800. Min Act: -0.1700
Data Index: 583229 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.3800. Min Act: -0.1700
Data Index: 2217145 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.3800. Min Act: -0.1700
Data Index: 1315735 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7550. Min Range: -5.7550
Max Act: 5.3800. Min Act: -0.1700
Data Index: 293843 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19