Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 999 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.8523. Min Act: -0.1700
Data Index: 4244402 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.5551. Min Act: -0.1700
Data Index: 4244409 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.3200. Min Act: -0.1700
Data Index: 4244400 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.2886. Min Act: -0.1700
Data Index: 5812226 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.2415. Min Act: -0.1700
Data Index: 4445437 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.2258. Min Act: -0.1700
Data Index: 672014 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.2100. Min Act: -0.1700
Data Index: 8695709 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.2729. Min Act: -0.1700
Data Index: 4244399 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.1786. Min Act: -0.1700
Data Index: 2779112 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.1786. Min Act: -0.1700
Data Index: 7542981 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.0999. Min Act: -0.1700
Data Index: 7875551 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.0999. Min Act: -0.1700
Data Index: 5467918 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.1156. Min Act: -0.1700
Data Index: 5839887 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.1156. Min Act: -0.1700
Data Index: 5047982 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.0999. Min Act: -0.1700
Data Index: 4244398 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.0683. Min Act: -0.1700
Data Index: 6934572 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.0683. Min Act: -0.1700
Data Index: 4244403 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.0683. Min Act: -0.1700
Data Index: 1730010 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.0683. Min Act: -0.1700
Data Index: 1964971 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8523. Min Range: -3.8523
Max Act: 3.0368. Min Act: -0.1700
Data Index: 4291682 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #19