Model: None
Dataset: The Pile
Neuron 1956 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.6728. Min Act: -0.1700
Data Index: 9194476 (The Pile)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.5925. Min Act: -0.1700
Data Index: 6612120 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.5602. Min Act: -0.1700
Data Index: 5830971 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.5602. Min Act: -0.1700
Data Index: 2647246 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.5441. Min Act: -0.1700
Data Index: 4046358 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.5441. Min Act: -0.1700
Data Index: 1909605 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.5279. Min Act: -0.1700
Data Index: 7507024 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.5279. Min Act: -0.1700
Data Index: 5743877 (The Pile)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.5118. Min Act: -0.1700
Data Index: 8935985 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4956. Min Act: -0.1700
Data Index: 10337764 (The Pile)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4956. Min Act: -0.1700
Data Index: 6949344 (The Pile)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4956. Min Act: -0.1700
Data Index: 8943290 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4794. Min Act: -0.1700
Data Index: 4075795 (The Pile)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4794. Min Act: -0.1700
Data Index: 9923031 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4794. Min Act: -0.1700
Data Index: 3925148 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4794. Min Act: -0.1700
Data Index: 2905541 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4794. Min Act: -0.1700
Data Index: 3586058 (The Pile)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4794. Min Act: -0.1700
Data Index: 2127355 (The Pile)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4794. Min Act: -0.1700
Data Index: 3544749 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6728. Min Range: -2.6728
Max Act: 2.4794. Min Act: -0.1700
Data Index: 8652876 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19