Model: None
Dataset: The Pile
Neuron 1539 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.3410. Min Act: -0.1700
Data Index: 9753093 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2939. Min Act: -0.1700
Data Index: 5098608 (The Pile)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2624. Min Act: -0.1700
Data Index: 3471607 (The Pile)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2310. Min Act: -0.1700
Data Index: 8929010 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1681. Min Act: -0.1700
Data Index: 10730357 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1523. Min Act: -0.1700
Data Index: 2150676 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1366. Min Act: -0.1700
Data Index: 8143631 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1208. Min Act: -0.1700
Data Index: 6218911 (The Pile)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1051. Min Act: -0.1700
Data Index: 10018209 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0893. Min Act: -0.1700
Data Index: 2116602 (The Pile)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0577. Min Act: -0.1700
Data Index: 8390544 (The Pile)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1051. Min Act: -0.1700
Data Index: 2194966 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1208. Min Act: -0.1700
Data Index: 7811385 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1051. Min Act: -0.1700
Data Index: 4813362 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0893. Min Act: -0.1700
Data Index: 3365507 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0893. Min Act: -0.1700
Data Index: 1270723 (The Pile)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0893. Min Act: -0.1700
Data Index: 2922284 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0735. Min Act: -0.1700
Data Index: 8647769 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1051. Min Act: -0.1700
Data Index: 8836150 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.0893. Min Act: -0.1700
Data Index: 5955071 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #19