Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3590 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.6012. Min Act: -0.1700
Data Index: 6305912 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.5542. Min Act: -0.1700
Data Index: 5010147 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.5698. Min Act: -0.1700
Data Index: 3882220 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.5385. Min Act: -0.1700
Data Index: 1331966 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.5229. Min Act: -0.1700
Data Index: 3104981 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.4916. Min Act: -0.1700
Data Index: 390968 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.4916. Min Act: -0.1700
Data Index: 3698804 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.4602. Min Act: -0.1700
Data Index: 1598113 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.4446. Min Act: -0.1700
Data Index: 7489277 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.4446. Min Act: -0.1700
Data Index: 2084169 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.4289. Min Act: -0.1700
Data Index: 4898497 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.3975. Min Act: -0.1700
Data Index: 6941230 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.3818. Min Act: -0.1700
Data Index: 816756 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.3818. Min Act: -0.1700
Data Index: 3662753 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.3662. Min Act: -0.1700
Data Index: 463280 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.3505. Min Act: -0.1700
Data Index: 7803959 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.3662. Min Act: -0.1700
Data Index: 7656655 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.3505. Min Act: -0.1700
Data Index: 5810564 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.3505. Min Act: -0.1700
Data Index: 4139338 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6012. Min Range: -3.6012
Max Act: 3.3505. Min Act: -0.1700
Data Index: 3786090 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19