Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1622 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.5054. Min Act: -0.1700
Data Index: 1818037 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3804. Min Act: -0.1700
Data Index: 3934445 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3804. Min Act: -0.1700
Data Index: 2109771 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.4117. Min Act: -0.1700
Data Index: 192989 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3492. Min Act: -0.1700
Data Index: 1411625 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3492. Min Act: -0.1700
Data Index: 5809533 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3179. Min Act: -0.1700
Data Index: 6041654 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3492. Min Act: -0.1700
Data Index: 8396028 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3179. Min Act: -0.1700
Data Index: 7864046 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3179. Min Act: -0.1700
Data Index: 4161342 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3179. Min Act: -0.1700
Data Index: 6157812 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2867. Min Act: -0.1700
Data Index: 4992028 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3179. Min Act: -0.1700
Data Index: 1256980 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2867. Min Act: -0.1700
Data Index: 5721828 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2867. Min Act: -0.1700
Data Index: 3892069 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.3179. Min Act: -0.1700
Data Index: 8114742 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2867. Min Act: -0.1700
Data Index: 659080 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2867. Min Act: -0.1700
Data Index: 1583465 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2867. Min Act: -0.1700
Data Index: 702188 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5054. Min Range: -4.5054
Max Act: 4.2554. Min Act: -0.1700
Data Index: 1715813 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19