Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4065 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1743. Min Range: -6.1743
Max Act: 6.1743. Min Act: -0.1700
Data Index: 838150 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1743. Min Range: -6.1743
Max Act: 6.1431. Min Act: -0.1700
Data Index: 8712680 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.9243. Min Act: -0.1700
Data Index: 424280 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.9243. Min Act: -0.1700
Data Index: 6170253 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.8931. Min Act: -0.1700
Data Index: 964632 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7993. Min Act: -0.1700
Data Index: 3017702 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.8306. Min Act: -0.1700
Data Index: 4071458 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7681. Min Act: -0.1700
Data Index: 4235167 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7681. Min Act: -0.1700
Data Index: 7552703 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7993. Min Act: -0.1700
Data Index: 1537800 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7056. Min Act: -0.1700
Data Index: 2861408 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7368. Min Act: -0.1700
Data Index: 4880976 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7368. Min Act: -0.1700
Data Index: 2797147 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7368. Min Act: -0.1700
Data Index: 2248450 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7368. Min Act: -0.1700
Data Index: 5641482 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7056. Min Act: -0.1700
Data Index: 2314588 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7056. Min Act: -0.1700
Data Index: 8509380 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7056. Min Act: -0.1700
Data Index: 8156991 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.7056. Min Act: -0.1700
Data Index: 2107471 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1743. Min Range: -6.1743
Max Act: 5.6743. Min Act: -0.1700
Data Index: 387155 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19