Model: None
Dataset: The Pile
Neuron 1708 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 51.4650. Min Range: -51.4650
Max Act: 51.4650. Min Act: -0.0113
Data Index: 2355110 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.9650. Min Act: -0.0997
Data Index: 8611559 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.9650. Min Act: -0.0997
Data Index: 6867236 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.0033
Data Index: 9635400 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.0958
Data Index: 385941 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.0663
Data Index: 6680557 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.1391
Data Index: 6493355 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.0630
Data Index: 3017565 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.1077
Data Index: 7709772 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.1691
Data Index: 7708693 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.0009
Data Index: 5233661 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.1462
Data Index: 3709236 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.0154
Data Index: 5118339 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.1238
Data Index: 302478 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.1651
Data Index: 4034745 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.1238
Data Index: 1080514 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.7150. Min Act: -0.1665
Data Index: 1369165 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.4650. Min Act: -0.0001
Data Index: 3718270 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.4650. Min Act: -0.0452
Data Index: 8967236 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 51.4650. Min Range: -51.4650
Max Act: 50.4650. Min Act: -0.0008
Data Index: 1356215 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19