Model: None
Dataset: The Pile
Neuron 4004 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.6093. Min Act: -0.1700
Data Index: 8969392 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5932. Min Act: -0.1700
Data Index: 10381098 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 2572271 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 7687072 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 7512237 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 6692680 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 7368127 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 521504 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 6249701 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 4516049 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 5521024 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 3888651 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 7005303 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 6741023 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 1436105 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 5311441 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 485013 (The Pile)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 1023053 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 6734256 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6093. Min Range: -2.6093
Max Act: 2.5771. Min Act: -0.1700
Data Index: 1908851 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19