Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 491 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.6981. Min Act: -0.1700
Data Index: 3903657 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.5106. Min Act: -0.1700
Data Index: 6530644 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.4169. Min Act: -0.1700
Data Index: 4422824 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.2606. Min Act: -0.1700
Data Index: 232218 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.2606. Min Act: -0.1700
Data Index: 1422369 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.2606. Min Act: -0.1700
Data Index: 936751 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.2293. Min Act: -0.1700
Data Index: 8381353 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.2293. Min Act: -0.1700
Data Index: 2196076 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1981. Min Act: -0.1700
Data Index: 100356 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1981. Min Act: -0.1700
Data Index: 5587895 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1668. Min Act: -0.1700
Data Index: 2148779 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1668. Min Act: -0.1700
Data Index: 7490889 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1981. Min Act: -0.1700
Data Index: 8122263 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1668. Min Act: -0.1700
Data Index: 5116167 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1668. Min Act: -0.1700
Data Index: 801629 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1668. Min Act: -0.1700
Data Index: 7513165 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1668. Min Act: -0.1700
Data Index: 3952127 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1043. Min Act: -0.1700
Data Index: 1835636 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1356. Min Act: -0.1700
Data Index: 1485239 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6981. Min Range: -4.6981
Max Act: 4.1356. Min Act: -0.1700
Data Index: 2801610 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19