Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 2003 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.4751. Min Act: -0.1700
Data Index: 4034246 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.4439. Min Act: -0.1700
Data Index: 535015 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.4126. Min Act: -0.1700
Data Index: 4419672 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.3501. Min Act: -0.1700
Data Index: 1648609 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.3189. Min Act: -0.1700
Data Index: 4000570 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.3189. Min Act: -0.1700
Data Index: 3909626 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.2876. Min Act: -0.1700
Data Index: 8401472 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.2564. Min Act: -0.1700
Data Index: 4786636 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.2564. Min Act: -0.1700
Data Index: 7842910 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1939. Min Act: -0.1700
Data Index: 7049794 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.2251. Min Act: -0.1700
Data Index: 605689 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1939. Min Act: -0.1700
Data Index: 7794164 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1939. Min Act: -0.1700
Data Index: 7582128 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1626. Min Act: -0.1700
Data Index: 3984484 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1626. Min Act: -0.1700
Data Index: 1291453 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1314. Min Act: -0.1700
Data Index: 3765218 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1939. Min Act: -0.1700
Data Index: 6402121 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1626. Min Act: -0.1700
Data Index: 7856091 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1939. Min Act: -0.1700
Data Index: 5564017 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4751. Min Range: -6.4751
Max Act: 6.1626. Min Act: -0.1700
Data Index: 7100759 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19