Model: None
Dataset: The Pile
Neuron 485 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.3532. Min Act: -0.1700
Data Index: 2591976 (The Pile)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.3532. Min Act: -0.1700
Data Index: 1071685 (The Pile)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.3220. Min Act: -0.1700
Data Index: 4818275 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.2282. Min Act: -0.1700
Data Index: 6023415 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.2594. Min Act: -0.1700
Data Index: 657778 (The Pile)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.2282. Min Act: -0.1700
Data Index: 7049592 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.2282. Min Act: -0.1700
Data Index: 5930556 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1657. Min Act: -0.1700
Data Index: 9194255 (The Pile)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.2282. Min Act: -0.1700
Data Index: 8775844 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1969. Min Act: -0.1700
Data Index: 3479841 (The Pile)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1969. Min Act: -0.1700
Data Index: 2618618 (The Pile)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1344. Min Act: -0.1700
Data Index: 4798731 (The Pile)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1657. Min Act: -0.1700
Data Index: 4342972 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1657. Min Act: -0.1700
Data Index: 2126535 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1344. Min Act: -0.1700
Data Index: 405862 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1657. Min Act: -0.1700
Data Index: 5496892 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1032. Min Act: -0.1700
Data Index: 999081 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1344. Min Act: -0.1700
Data Index: 10529322 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1344. Min Act: -0.1700
Data Index: 6361965 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3532. Min Range: -4.3532
Max Act: 4.1032. Min Act: -0.1700
Data Index: 4134588 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19