Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0523. Min Range: -6.0523
Max Act: 6.0523. Min Act: -0.1700
Data Index: 5082109 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.9586. Min Act: -0.1700
Data Index: 870914 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.8961. Min Act: -0.1700
Data Index: 3676868 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.8648. Min Act: -0.1700
Data Index: 5335755 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.8961. Min Act: -0.1700
Data Index: 6090982 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.8648. Min Act: -0.1700
Data Index: 3341695 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.8336. Min Act: -0.1700
Data Index: 6129788 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.8336. Min Act: -0.1700
Data Index: 870926 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.8023. Min Act: -0.1700
Data Index: 1353676 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.8023. Min Act: -0.1700
Data Index: 3047538 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.7398. Min Act: -0.1700
Data Index: 6833413 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.7711. Min Act: -0.1700
Data Index: 1964573 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.7398. Min Act: -0.1700
Data Index: 128922 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.7398. Min Act: -0.1700
Data Index: 2041731 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.7086. Min Act: -0.1700
Data Index: 4131665 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.7086. Min Act: -0.1700
Data Index: 6035528 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.7086. Min Act: -0.1700
Data Index: 3106678 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.7086. Min Act: -0.1700
Data Index: 8713058 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.7086. Min Act: -0.1700
Data Index: 3844207 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0523. Min Range: -6.0523
Max Act: 5.7398. Min Act: -0.1700
Data Index: 5726706 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19