Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3392 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2626. Min Range: -4.2626
Max Act: 4.2626. Min Act: -0.1700
Data Index: 5487501 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2626. Min Range: -4.2626
Max Act: 4.2314. Min Act: -0.1700
Data Index: 964143 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2626. Min Range: -4.2626
Max Act: 4.2001. Min Act: -0.1699
Data Index: 3506537 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2626. Min Range: -4.2626
Max Act: 4.1689. Min Act: -0.1700
Data Index: 8044695 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2626. Min Range: -4.2626
Max Act: 4.0439. Min Act: -0.1700
Data Index: 3928076 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2626. Min Range: -4.2626
Max Act: 4.0126. Min Act: -0.1700
Data Index: 5490355 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.9813. Min Act: -0.1700
Data Index: 239002 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.9813. Min Act: -0.1700
Data Index: 6402591 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.9813. Min Act: -0.1700
Data Index: 3031161 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.9188. Min Act: -0.1700
Data Index: 321839 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.9501. Min Act: -0.1700
Data Index: 8328961 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.9188. Min Act: -0.1700
Data Index: 1625246 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.8875. Min Act: -0.1700
Data Index: 4411730 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.8875. Min Act: -0.1700
Data Index: 3600166 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.8875. Min Act: -0.1700
Data Index: 7657444 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.8563. Min Act: -0.1700
Data Index: 1496091 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.8563. Min Act: -0.1700
Data Index: 7040841 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.8563. Min Act: -0.1700
Data Index: 7066706 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.8875. Min Act: -0.1700
Data Index: 3832621 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2626. Min Range: -4.2626
Max Act: 3.8563. Min Act: -0.1700
Data Index: 2853158 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19