Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.5536. Min Act: -0.1700
Data Index: 5799005 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.5536. Min Act: -0.1700
Data Index: 5427053 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.5223. Min Act: -0.1700
Data Index: 8014394 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4909. Min Act: -0.1700
Data Index: 4587187 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4909. Min Act: -0.1700
Data Index: 4981399 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4909. Min Act: -0.1700
Data Index: 8059810 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4596. Min Act: -0.1700
Data Index: 4474448 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4596. Min Act: -0.1700
Data Index: 3400579 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4596. Min Act: -0.1700
Data Index: 2931469 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4596. Min Act: -0.1700
Data Index: 4293794 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4283. Min Act: -0.1700
Data Index: 5329213 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4283. Min Act: -0.1700
Data Index: 1136394 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4283. Min Act: -0.1700
Data Index: 3028592 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4283. Min Act: -0.1700
Data Index: 5434332 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4283. Min Act: -0.1700
Data Index: 5995035 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4283. Min Act: -0.1700
Data Index: 6959349 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4283. Min Act: -0.1700
Data Index: 7701674 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4283. Min Act: -0.1700
Data Index: 422215 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.4283. Min Act: -0.1700
Data Index: 54582 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5536. Min Range: -3.5536
Max Act: 3.3969. Min Act: -0.1700
Data Index: 143075 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19