Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4983 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.8800. Min Act: -0.1700
Data Index: 4122053 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.6613. Min Act: -0.1700
Data Index: 7561007 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.6613. Min Act: -0.1700
Data Index: 4220060 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.6300. Min Act: -0.1700
Data Index: 2231052 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5988. Min Act: -0.1700
Data Index: 6652210 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.6300. Min Act: -0.1700
Data Index: 8430860 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.6300. Min Act: -0.1700
Data Index: 2239590 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5988. Min Act: -0.1700
Data Index: 5522365 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5988. Min Act: -0.1700
Data Index: 4135488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5988. Min Act: -0.1700
Data Index: 4876577 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5988. Min Act: -0.1700
Data Index: 8714386 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5988. Min Act: -0.1700
Data Index: 1011261 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5988. Min Act: -0.1700
Data Index: 7909730 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5988. Min Act: -0.1700
Data Index: 4450009 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5988. Min Act: -0.1700
Data Index: 5342675 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5363. Min Act: -0.1700
Data Index: 1273062 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5675. Min Act: -0.1700
Data Index: 6336881 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5675. Min Act: -0.1700
Data Index: 374728 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5363. Min Act: -0.1700
Data Index: 3429295 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8800. Min Range: -4.8800
Max Act: 4.5363. Min Act: -0.1700
Data Index: 4405160 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19