Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1620 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.5749. Min Act: -0.1700
Data Index: 785050 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.4499. Min Act: -0.1700
Data Index: 4891015 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.3562. Min Act: -0.1700
Data Index: 3699470 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.3249. Min Act: -0.1700
Data Index: 8764579 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.2624. Min Act: -0.1700
Data Index: 3459301 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.2312. Min Act: -0.1700
Data Index: 8549011 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.1999. Min Act: -0.1700
Data Index: 1625252 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.1999. Min Act: -0.1700
Data Index: 1060861 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.1687. Min Act: -0.1700
Data Index: 8370494 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.1687. Min Act: -0.1700
Data Index: 930600 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.1687. Min Act: -0.1700
Data Index: 1462367 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.0437. Min Act: -0.1700
Data Index: 4930356 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.0749. Min Act: -0.1700
Data Index: 3032412 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.0437. Min Act: -0.1700
Data Index: 930598 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.0437. Min Act: -0.1700
Data Index: 7048732 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.0437. Min Act: -0.1700
Data Index: 1814989 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.0437. Min Act: -0.1700
Data Index: 5674088 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.0124. Min Act: -0.1700
Data Index: 4388369 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.0437. Min Act: -0.1700
Data Index: 692826 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5749. Min Range: -6.5749
Max Act: 6.0124. Min Act: -0.1700
Data Index: 3483407 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19