Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.3622. Min Act: -0.1700
Data Index: 5362750 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.1435. Min Act: -0.1700
Data Index: 1923854 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3622. Min Range: -4.3622
Max Act: 4.0497. Min Act: -0.1700
Data Index: 335231 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.9559. Min Act: -0.1700
Data Index: 302497 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.9246. Min Act: -0.1700
Data Index: 5755473 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.8934. Min Act: -0.1700
Data Index: 8610832 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.9246. Min Act: -0.1700
Data Index: 8698050 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.8934. Min Act: -0.1700
Data Index: 7442947 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.8621. Min Act: -0.1700
Data Index: 4956069 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.8934. Min Act: -0.1700
Data Index: 5820923 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.8621. Min Act: -0.1700
Data Index: 1655802 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.8308. Min Act: -0.1700
Data Index: 2680493 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.7996. Min Act: -0.1700
Data Index: 5774728 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.8308. Min Act: -0.1700
Data Index: 1040768 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.7996. Min Act: -0.1700
Data Index: 4543235 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.7996. Min Act: -0.1700
Data Index: 5755474 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.7996. Min Act: -0.1700
Data Index: 8311775 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.8308. Min Act: -0.1700
Data Index: 2185940 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.7996. Min Act: -0.1700
Data Index: 7159661 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3622. Min Range: -4.3622
Max Act: 3.7996. Min Act: -0.1700
Data Index: 5554604 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19