Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2150 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.9053. Min Act: -0.1700
Data Index: 2551466 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.8428. Min Act: -0.1700
Data Index: 8374400 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.8115. Min Act: -0.1700
Data Index: 1412400 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.5615. Min Act: -0.1700
Data Index: 3550708 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.5303. Min Act: -0.1700
Data Index: 4887905 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4990. Min Act: -0.1700
Data Index: 1537299 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.5303. Min Act: -0.1700
Data Index: 4612851 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.5303. Min Act: -0.1700
Data Index: 6983023 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.5303. Min Act: -0.1700
Data Index: 2068952 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4678. Min Act: -0.1700
Data Index: 5761208 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4678. Min Act: -0.1700
Data Index: 6576833 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4678. Min Act: -0.1700
Data Index: 6510759 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4365. Min Act: -0.1700
Data Index: 5430295 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4365. Min Act: -0.1700
Data Index: 8464151 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4365. Min Act: -0.1700
Data Index: 1513827 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4053. Min Act: -0.1700
Data Index: 3433106 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4365. Min Act: -0.1700
Data Index: 5893536 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4365. Min Act: -0.1700
Data Index: 6975244 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.4053. Min Act: -0.1700
Data Index: 1497951 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9053. Min Range: -5.9053
Max Act: 5.3740. Min Act: -0.1700
Data Index: 5962897 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19