Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2791 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.3575. Min Act: -0.1700
Data Index: 1846783 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.3263. Min Act: -0.1700
Data Index: 4639746 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.3263. Min Act: -0.1700
Data Index: 2921666 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.2325. Min Act: -0.1699
Data Index: 5070898 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.2013. Min Act: -0.1700
Data Index: 2705713 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.2013. Min Act: -0.1700
Data Index: 4484316 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.1700. Min Act: -0.1700
Data Index: 6549815 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.1700. Min Act: -0.1700
Data Index: 4434973 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.1388. Min Act: -0.1700
Data Index: 4105675 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.1075. Min Act: -0.1700
Data Index: 6298833 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.1388. Min Act: -0.1699
Data Index: 5037840 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.1388. Min Act: -0.1700
Data Index: 1955979 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.1075. Min Act: -0.1700
Data Index: 456135 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.1388. Min Act: -0.1700
Data Index: 1890802 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.0763. Min Act: -0.1700
Data Index: 7151999 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.0450. Min Act: -0.1700
Data Index: 6646152 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.0450. Min Act: -0.1700
Data Index: 2885093 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.0763. Min Act: -0.1700
Data Index: 2571233 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.0450. Min Act: -0.1700
Data Index: 790879 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3575. Min Range: -5.3575
Max Act: 5.1075. Min Act: -0.1699
Data Index: 1056622 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19