Model: None
Dataset: The Pile
Neuron 1704 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.3238. Min Act: -0.1700
Data Index: 9532326 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2924. Min Act: -0.1700
Data Index: 4304170 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2766. Min Act: -0.1700
Data Index: 5636303 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2452. Min Act: -0.1700
Data Index: 10338864 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2452. Min Act: -0.1700
Data Index: 6158076 (The Pile)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2295. Min Act: -0.1700
Data Index: 848053 (The Pile)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2138. Min Act: -0.1700
Data Index: 10139978 (The Pile)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2138. Min Act: -0.1700
Data Index: 947408 (The Pile)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2138. Min Act: -0.1700
Data Index: 2515929 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2138. Min Act: -0.1700
Data Index: 3357736 (The Pile)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.2138. Min Act: -0.1700
Data Index: 90141 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1980. Min Act: -0.1700
Data Index: 2086496 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1980. Min Act: -0.1700
Data Index: 8416459 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1980. Min Act: -0.1700
Data Index: 2426786 (The Pile)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1980. Min Act: -0.1700
Data Index: 5148443 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1980. Min Act: -0.1700
Data Index: 2628566 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1980. Min Act: -0.1700
Data Index: 10577129 (The Pile)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1823. Min Act: -0.1700
Data Index: 6253462 (The Pile)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1823. Min Act: -0.1700
Data Index: 2254868 (The Pile)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3238. Min Range: -3.3238
Max Act: 3.1823. Min Act: -0.1700
Data Index: 8266224 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19