Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3734 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0735. Min Range: -4.0735
Max Act: 4.0735. Min Act: -0.1700
Data Index: 4479544 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.9797. Min Act: -0.1700
Data Index: 4534706 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.9797. Min Act: -0.1700
Data Index: 4142225 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.9797. Min Act: -0.1700
Data Index: 5061001 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.9484. Min Act: -0.1700
Data Index: 5212224 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.8859. Min Act: -0.1700
Data Index: 6017938 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.8859. Min Act: -0.1700
Data Index: 4792756 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.9172. Min Act: -0.1700
Data Index: 4879882 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.8546. Min Act: -0.1700
Data Index: 2585878 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.8234. Min Act: -0.1700
Data Index: 514186 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.7921. Min Act: -0.1700
Data Index: 6155841 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.7921. Min Act: -0.1700
Data Index: 5411151 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.7921. Min Act: -0.1700
Data Index: 6761155 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.7921. Min Act: -0.1700
Data Index: 7026696 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.7921. Min Act: -0.1700
Data Index: 5887212 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.7608. Min Act: -0.1700
Data Index: 4460076 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.7921. Min Act: -0.1700
Data Index: 8216862 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.7608. Min Act: -0.1700
Data Index: 6343205 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.7608. Min Act: -0.1700
Data Index: 6230846 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0735. Min Range: -4.0735
Max Act: 3.7608. Min Act: -0.1700
Data Index: 7647126 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19