Model: None
Dataset: The Pile
Neuron 804 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.3108. Min Act: -0.1700
Data Index: 9901094 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.3108. Min Act: -0.1700
Data Index: 9416485 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.3422. Min Act: -0.1699
Data Index: 8635993 (The Pile)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.3422. Min Act: -0.1700
Data Index: 7168814 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2479. Min Act: -0.1700
Data Index: 664189 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2322. Min Act: -0.1700
Data Index: 2236761 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2793. Min Act: -0.1700
Data Index: 7150603 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2322. Min Act: -0.1700
Data Index: 4573751 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2165. Min Act: -0.1700
Data Index: 8068062 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2007. Min Act: -0.1700
Data Index: 6630487 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2322. Min Act: -0.1700
Data Index: 10369356 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.1850. Min Act: -0.1700
Data Index: 9350355 (The Pile)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2007. Min Act: -0.1700
Data Index: 6171122 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.1378. Min Act: -0.1700
Data Index: 2608489 (The Pile)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2165. Min Act: -0.1700
Data Index: 3241412 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2322. Min Act: -0.1700
Data Index: 7237431 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.1850. Min Act: -0.1700
Data Index: 2396675 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.0747. Min Act: -0.1700
Data Index: 817348 (The Pile)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2165. Min Act: -0.1700
Data Index: 3584448 (The Pile)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3422. Min Range: -3.3422
Max Act: 3.2165. Min Act: -0.1700
Data Index: 5909044 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19