Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.3137. Min Act: -0.1700
Data Index: 6298728 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.2200. Min Act: -0.1700
Data Index: 1458752 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.2200. Min Act: -0.1700
Data Index: 8042673 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.2200. Min Act: -0.1700
Data Index: 2643928 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1575. Min Act: -0.1700
Data Index: 2860783 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 5607033 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 7357037 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 8236906 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 3639772 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.1262. Min Act: -0.1700
Data Index: 2457638 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.0950. Min Act: -0.1700
Data Index: 46052 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.0950. Min Act: -0.1700
Data Index: 1687060 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.0637. Min Act: -0.1700
Data Index: 1193413 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.0325. Min Act: -0.1700
Data Index: 7304290 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.0012. Min Act: -0.1700
Data Index: 3554848 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3137. Min Range: -5.3137
Max Act: 4.9700. Min Act: -0.1700
Data Index: 2571454 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3137. Min Range: -5.3137
Max Act: 5.0012. Min Act: -0.1700
Data Index: 4348618 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3137. Min Range: -5.3137
Max Act: 4.9700. Min Act: -0.1700
Data Index: 3385054 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3137. Min Range: -5.3137
Max Act: 4.9387. Min Act: -0.1700
Data Index: 6946522 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3137. Min Range: -5.3137
Max Act: 4.9387. Min Act: -0.1700
Data Index: 4061770 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19