Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1061 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.6861. Min Act: -0.1700
Data Index: 4837518 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.6220. Min Act: -0.1700
Data Index: 3062715 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5898. Min Act: -0.1700
Data Index: 3052344 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.6059. Min Act: -0.1700
Data Index: 5453650 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.6059. Min Act: -0.1700
Data Index: 7014023 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5898. Min Act: -0.1700
Data Index: 7188242 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5898. Min Act: -0.1700
Data Index: 7534696 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5898. Min Act: -0.1700
Data Index: 6787600 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5737. Min Act: -0.1700
Data Index: 7572219 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5737. Min Act: -0.1700
Data Index: 8449158 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5576. Min Act: -0.1700
Data Index: 3154431 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5737. Min Act: -0.1700
Data Index: 3617817 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5737. Min Act: -0.1700
Data Index: 3920708 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5576. Min Act: -0.1700
Data Index: 6303251 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5576. Min Act: -0.1700
Data Index: 5671096 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5576. Min Act: -0.1700
Data Index: 5913061 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5576. Min Act: -0.1700
Data Index: 787780 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5576. Min Act: -0.1700
Data Index: 6556970 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5576. Min Act: -0.1700
Data Index: 6787598 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6861. Min Range: -2.6861
Max Act: 2.5576. Min Act: -0.1700
Data Index: 4814666 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19