Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 525 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.4183. Min Act: -0.1700
Data Index: 2141149 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.4183. Min Act: -0.1700
Data Index: 99957 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.4183. Min Act: -0.1700
Data Index: 3918078 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.3245. Min Act: -0.1700
Data Index: 2975308 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.2620. Min Act: -0.1700
Data Index: 3753861 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.2620. Min Act: -0.1700
Data Index: 5056248 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.2308. Min Act: -0.1700
Data Index: 5959452 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.2308. Min Act: -0.1700
Data Index: 4935864 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.2308. Min Act: -0.1700
Data Index: 1867639 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1995. Min Act: -0.1700
Data Index: 2548130 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1683. Min Act: -0.1700
Data Index: 5817710 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1370. Min Act: -0.1700
Data Index: 1867642 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1683. Min Act: -0.1700
Data Index: 4804662 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1683. Min Act: -0.1700
Data Index: 3280701 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1683. Min Act: -0.1700
Data Index: 812100 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1370. Min Act: -0.1700
Data Index: 4989957 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1370. Min Act: -0.1700
Data Index: 4145099 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1683. Min Act: -0.1700
Data Index: 467619 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1058. Min Act: -0.1700
Data Index: 2189040 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4183. Min Range: -5.4183
Max Act: 5.1370. Min Act: -0.1700
Data Index: 776972 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19