Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 939 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.9499. Min Act: -0.1700
Data Index: 4832527 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.8717. Min Act: -0.1700
Data Index: 1492660 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.8874. Min Act: -0.1700
Data Index: 8694865 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.8092. Min Act: -0.1700
Data Index: 4692643 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.8092. Min Act: -0.1700
Data Index: 7927301 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.8092. Min Act: -0.1700
Data Index: 246971 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7779. Min Act: -0.1700
Data Index: 8061691 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7623. Min Act: -0.1700
Data Index: 6933875 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7623. Min Act: -0.1700
Data Index: 6800113 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7779. Min Act: -0.1700
Data Index: 7380152 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7623. Min Act: -0.1700
Data Index: 1020883 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7623. Min Act: -0.1700
Data Index: 2708102 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7623. Min Act: -0.1700
Data Index: 1247557 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7466. Min Act: -0.1700
Data Index: 906061 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7466. Min Act: -0.1700
Data Index: 6242669 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7154. Min Act: -0.1700
Data Index: 7093334 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7154. Min Act: -0.1700
Data Index: 2982741 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7310. Min Act: -0.1700
Data Index: 7389513 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7466. Min Act: -0.1700
Data Index: 6757457 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9499. Min Range: -3.9499
Max Act: 3.7310. Min Act: -0.1700
Data Index: 5373909 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #19