Model: None
Dataset: The Pile
Neuron 3664 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.3041. Min Range: -4.3041
Max Act: 4.3041. Min Act: -0.1700
Data Index: 8804197 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.9915. Min Act: -0.1700
Data Index: 1009111 (The Pile)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.9603. Min Act: -0.1700
Data Index: 2273835 (The Pile)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.9290. Min Act: -0.1700
Data Index: 1900354 (The Pile)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.8977. Min Act: -0.1700
Data Index: 2372070 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.8977. Min Act: -0.1700
Data Index: 8065417 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.8977. Min Act: -0.1700
Data Index: 4350121 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.8821. Min Act: -0.1700
Data Index: 8741547 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.8664. Min Act: -0.1700
Data Index: 8263211 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.8039. Min Act: -0.1700
Data Index: 1316192 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.7882. Min Act: -0.1700
Data Index: 5147562 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.7882. Min Act: -0.1700
Data Index: 7494720 (The Pile)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.7882. Min Act: -0.1700
Data Index: 1695575 (The Pile)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.7882. Min Act: -0.1700
Data Index: 6226674 (The Pile)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.7570. Min Act: -0.1700
Data Index: 411565 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.7413. Min Act: -0.1700
Data Index: 9445935 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.7413. Min Act: -0.1700
Data Index: 3117949 (The Pile)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.7257. Min Act: -0.1700
Data Index: 1431406 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.7100. Min Act: -0.1700
Data Index: 1355495 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3041. Min Range: -4.3041
Max Act: 3.6944. Min Act: -0.1700
Data Index: 1027585 (The Pile)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19