Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2711 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.4846. Min Act: -0.1700
Data Index: 6179908 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.4221. Min Act: -0.1699
Data Index: 1789610 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.3908. Min Act: -0.1700
Data Index: 6227256 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.3908. Min Act: -0.1700
Data Index: 8802760 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.3283. Min Act: -0.1700
Data Index: 2012023 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.3283. Min Act: -0.1700
Data Index: 726617 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.3283. Min Act: -0.1699
Data Index: 2086067 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.3283. Min Act: -0.1700
Data Index: 3834736 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.3283. Min Act: -0.1700
Data Index: 6269731 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2971. Min Act: -0.1691
Data Index: 283820 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2971. Min Act: -0.1700
Data Index: 916151 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2971. Min Act: -0.1699
Data Index: 3468784 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2971. Min Act: -0.1700
Data Index: 4755278 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2971. Min Act: -0.1700
Data Index: 5956686 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2971. Min Act: -0.1700
Data Index: 1329987 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2658. Min Act: -0.1700
Data Index: 1597071 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2971. Min Act: -0.1698
Data Index: 2200189 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2658. Min Act: -0.1698
Data Index: 3986777 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2658. Min Act: -0.1700
Data Index: 4551333 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4846. Min Range: -5.4846
Max Act: 5.2971. Min Act: -0.1699
Data Index: 4769333 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #19