Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5167 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.9551. Min Act: -0.1700
Data Index: 4959147 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.9238. Min Act: -0.1700
Data Index: 1240001 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7676. Min Act: -0.1700
Data Index: 8421722 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7363. Min Act: -0.1700
Data Index: 5035913 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.7051. Min Act: -0.1700
Data Index: 1991556 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6738. Min Act: -0.1700
Data Index: 7686941 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6426. Min Act: -0.1700
Data Index: 1157356 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6426. Min Act: -0.1700
Data Index: 8529520 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6426. Min Act: -0.1700
Data Index: 8721093 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6113. Min Act: -0.1700
Data Index: 1843151 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6113. Min Act: -0.1700
Data Index: 3883766 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6113. Min Act: -0.1700
Data Index: 1252054 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6113. Min Act: -0.1700
Data Index: 2135469 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.5801. Min Act: -0.1700
Data Index: 7724151 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6113. Min Act: -0.1700
Data Index: 1171324 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.6113. Min Act: -0.1700
Data Index: 278744 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.5801. Min Act: -0.1700
Data Index: 1999582 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.5801. Min Act: -0.1700
Data Index: 6492249 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.5801. Min Act: -0.1699
Data Index: 7064103 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9551. Min Range: -4.9551
Max Act: 4.5801. Min Act: -0.1700
Data Index: 3358373 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19