Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.2494. Min Act: -0.1700
Data Index: 8551778 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.2180. Min Act: -0.1700
Data Index: 2065960 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.2494. Min Act: -0.1700
Data Index: 3301534 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.2022. Min Act: -0.1700
Data Index: 5876933 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1708. Min Act: -0.1700
Data Index: 1713863 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1708. Min Act: -0.1700
Data Index: 5876938 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1708. Min Act: -0.1700
Data Index: 5876932 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1550. Min Act: -0.1700
Data Index: 5876940 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1550. Min Act: -0.1700
Data Index: 5996694 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1550. Min Act: -0.1700
Data Index: 4402018 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1550. Min Act: -0.1700
Data Index: 1878944 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1393. Min Act: -0.1700
Data Index: 5876937 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1550. Min Act: -0.1700
Data Index: 4208735 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1393. Min Act: -0.1700
Data Index: 5876942 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1393. Min Act: -0.1700
Data Index: 5876931 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1550. Min Act: -0.1700
Data Index: 352109 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1550. Min Act: -0.1700
Data Index: 6458340 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1078. Min Act: -0.1700
Data Index: 8295051 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1236. Min Act: -0.1700
Data Index: 8024071 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2494. Min Range: -3.2494
Max Act: 3.1393. Min Act: -0.1700
Data Index: 5876925 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19