Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1909 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.5807. Min Act: -0.1700
Data Index: 30069 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.5495. Min Act: -0.1700
Data Index: 1181010 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.4870. Min Act: -0.1700
Data Index: 1623658 (Python Code)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.3932. Min Act: -0.1700
Data Index: 1228223 (C4 (Web Text))
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.3620. Min Act: -0.1700
Data Index: 532662 (C4 (Web Text))
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.3932. Min Act: -0.1699
Data Index: 1438656 (Python Code)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.3620. Min Act: -0.1700
Data Index: 1530867 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.3932. Min Act: -0.1700
Data Index: 1228993 (C4 (Web Text))
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.3932. Min Act: -0.1700
Data Index: 155954 (C4 (Web Text))
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.3620. Min Act: -0.1700
Data Index: 681831 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.3307. Min Act: -0.1700
Data Index: 1318220 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.3307. Min Act: -0.1700
Data Index: 297181 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.2995. Min Act: -0.1700
Data Index: 724047 (C4 (Web Text))
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.2370. Min Act: -0.1700
Data Index: 208852 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.2526. Min Act: -0.1700
Data Index: 1255389 (C4 (Web Text))
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.2995. Min Act: -0.1700
Data Index: 1015602 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.2995. Min Act: -0.1700
Data Index: 1121085 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.3307. Min Act: -0.1700
Data Index: 350803 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.2682. Min Act: -0.1700
Data Index: 73036 (C4 (Web Text))
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5807. Min Range: -4.5807
Max Act: 4.2370. Min Act: -0.1700
Data Index: 869237 (C4 (Web Text))
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19