Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2833. Min Act: -0.1700
Data Index: 1750548 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2518. Min Act: -0.1700
Data Index: 5295122 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2518. Min Act: -0.1700
Data Index: 2942509 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2518. Min Act: -0.1700
Data Index: 7636306 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2361. Min Act: -0.1700
Data Index: 2788481 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2361. Min Act: -0.1700
Data Index: 3581304 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2361. Min Act: -0.1700
Data Index: 4677201 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2518. Min Act: -0.1700
Data Index: 7663267 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2204. Min Act: -0.1700
Data Index: 4135484 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2204. Min Act: -0.1700
Data Index: 2695222 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2204. Min Act: -0.1700
Data Index: 7297607 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2204. Min Act: -0.1700
Data Index: 2311094 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.2047. Min Act: -0.1700
Data Index: 241415 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.1890. Min Act: -0.1700
Data Index: 7433115 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.1890. Min Act: -0.1700
Data Index: 31521 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.1732. Min Act: -0.1700
Data Index: 3071186 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.1890. Min Act: -0.1700
Data Index: 5753947 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.1890. Min Act: -0.1700
Data Index: 2414374 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.1890. Min Act: -0.1700
Data Index: 3855400 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2833. Min Range: -3.2833
Max Act: 3.1732. Min Act: -0.1700
Data Index: 1785840 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19