Model: None
Dataset: The Pile
Neuron 905 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.4737. Min Act: -0.1700
Data Index: 6390576 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.4110. Min Act: -0.1700
Data Index: 2429808 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3639. Min Act: -0.1700
Data Index: 7763427 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3482. Min Act: -0.1700
Data Index: 3590882 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3482. Min Act: -0.1700
Data Index: 4275899 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3325. Min Act: -0.1700
Data Index: 4391273 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3325. Min Act: -0.1700
Data Index: 6246147 (The Pile)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3168. Min Act: -0.1700
Data Index: 10751278 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3168. Min Act: -0.1700
Data Index: 4881318 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3168. Min Act: -0.1700
Data Index: 2692867 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3011. Min Act: -0.1700
Data Index: 9670920 (The Pile)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3011. Min Act: -0.1700
Data Index: 7241382 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3011. Min Act: -0.1700
Data Index: 799736 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.3011. Min Act: -0.1700
Data Index: 3960415 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.2854. Min Act: -0.1700
Data Index: 3823458 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.2854. Min Act: -0.1700
Data Index: 10735870 (The Pile)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.2854. Min Act: -0.1700
Data Index: 1963232 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.2854. Min Act: -0.1700
Data Index: 9073975 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.2697. Min Act: -0.1700
Data Index: 6345542 (The Pile)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4737. Min Range: -3.4737
Max Act: 3.2697. Min Act: -0.1700
Data Index: 3952608 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19