Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2905 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1023. Min Range: -5.1023
Max Act: 5.1023. Min Act: -0.1700
Data Index: 8803117 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1023. Min Range: -5.1023
Max Act: 5.1023. Min Act: -0.1700
Data Index: 8134415 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1023. Min Range: -5.1023
Max Act: 5.1023. Min Act: -0.1700
Data Index: 2880145 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1023. Min Range: -5.1023
Max Act: 5.1023. Min Act: -0.1700
Data Index: 90142 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1023. Min Range: -5.1023
Max Act: 5.1023. Min Act: -0.1700
Data Index: 4366143 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1023. Min Range: -5.1023
Max Act: 5.0711. Min Act: -0.1700
Data Index: 8399533 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1023. Min Range: -5.1023
Max Act: 5.0711. Min Act: -0.1700
Data Index: 2461219 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1023. Min Range: -5.1023
Max Act: 5.0086. Min Act: -0.1700
Data Index: 3327112 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1023. Min Range: -5.1023
Max Act: 5.0398. Min Act: -0.1700
Data Index: 3952818 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1023. Min Range: -5.1023
Max Act: 5.0086. Min Act: -0.1700
Data Index: 429897 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1023. Min Range: -5.1023
Max Act: 4.9773. Min Act: -0.1700
Data Index: 3200091 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1023. Min Range: -5.1023
Max Act: 4.9461. Min Act: -0.1700
Data Index: 5072117 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1023. Min Range: -5.1023
Max Act: 4.9148. Min Act: -0.1700
Data Index: 5443394 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1023. Min Range: -5.1023
Max Act: 4.9461. Min Act: -0.1700
Data Index: 7172207 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1023. Min Range: -5.1023
Max Act: 4.9461. Min Act: -0.1700
Data Index: 6969126 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1023. Min Range: -5.1023
Max Act: 4.9461. Min Act: -0.1700
Data Index: 634183 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1023. Min Range: -5.1023
Max Act: 4.9461. Min Act: -0.1700
Data Index: 3720431 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1023. Min Range: -5.1023
Max Act: 4.9461. Min Act: -0.1700
Data Index: 1372078 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1023. Min Range: -5.1023
Max Act: 4.9461. Min Act: -0.1700
Data Index: 1045627 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1023. Min Range: -5.1023
Max Act: 4.9461. Min Act: -0.1700
Data Index: 6739668 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19