Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2998 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.9680. Min Act: -0.1700
Data Index: 8526743 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.8118. Min Act: -0.1700
Data Index: 1203638 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7805. Min Act: -0.1700
Data Index: 1714535 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7493. Min Act: -0.1700
Data Index: 5659341 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 2230333 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 3768844 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4770009 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 2754587 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 2597192 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 988692 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 1534917 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 4173586 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 250382 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1696
Data Index: 1741993 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 2143212 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 3607987 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 1084447 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 1992520 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 3410248 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9680. Min Range: -5.9680
Max Act: 5.7180. Min Act: -0.1700
Data Index: 3101431 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19