Model: None
Dataset: The Pile
Neuron 793 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.3786. Min Act: -0.1700
Data Index: 3835668 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.3459. Min Act: -0.1700
Data Index: 3724854 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.3295. Min Act: -0.1700
Data Index: 1021156 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.3459. Min Act: -0.1700
Data Index: 5632461 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.3131. Min Act: -0.1700
Data Index: 4889310 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2637. Min Act: -0.1700
Data Index: 10263260 (The Pile)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2472. Min Act: -0.1700
Data Index: 965748 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2472. Min Act: -0.1700
Data Index: 330515 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2472. Min Act: -0.1700
Data Index: 1119793 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2307. Min Act: -0.1700
Data Index: 6042068 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2307. Min Act: -0.1700
Data Index: 854890 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2307. Min Act: -0.1700
Data Index: 6740714 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2307. Min Act: -0.1700
Data Index: 2111759 (The Pile)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2307. Min Act: -0.1700
Data Index: 877088 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2307. Min Act: -0.1700
Data Index: 2782239 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2307. Min Act: -0.1700
Data Index: 7839811 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2141. Min Act: -0.1700
Data Index: 3119952 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2141. Min Act: -0.1700
Data Index: 1429545 (The Pile)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2307. Min Act: -0.1700
Data Index: 2935749 (The Pile)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3786. Min Range: -2.3786
Max Act: 2.2141. Min Act: -0.1700
Data Index: 2916142 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19