Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 745 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3886. Min Range: -4.3886
Max Act: 4.3886. Min Act: -0.1700
Data Index: 6265853 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3886. Min Range: -4.3886
Max Act: 4.2010. Min Act: -0.1700
Data Index: 845314 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3886. Min Range: -4.3886
Max Act: 4.2010. Min Act: -0.1700
Data Index: 5358898 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3886. Min Range: -4.3886
Max Act: 4.1073. Min Act: -0.1700
Data Index: 8513906 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3886. Min Range: -4.3886
Max Act: 4.1073. Min Act: -0.1700
Data Index: 2555956 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3886. Min Range: -4.3886
Max Act: 4.0760. Min Act: -0.1700
Data Index: 5061924 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3886. Min Range: -4.3886
Max Act: 4.0135. Min Act: -0.1700
Data Index: 1181941 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3886. Min Range: -4.3886
Max Act: 4.0135. Min Act: -0.1700
Data Index: 246974 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.9510. Min Act: -0.1700
Data Index: 2198421 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.9197. Min Act: -0.1700
Data Index: 2133943 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.9353. Min Act: -0.1700
Data Index: 4527973 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.9353. Min Act: -0.1700
Data Index: 4869965 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.9353. Min Act: -0.1700
Data Index: 740209 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.8884. Min Act: -0.1700
Data Index: 8088120 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.9041. Min Act: -0.1700
Data Index: 6875845 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.8572. Min Act: -0.1700
Data Index: 3577852 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.8572. Min Act: -0.1700
Data Index: 1884055 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.7946. Min Act: -0.1700
Data Index: 6083874 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.7946. Min Act: -0.1700
Data Index: 6263755 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3886. Min Range: -4.3886
Max Act: 3.8103. Min Act: -0.1700
Data Index: 5537661 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19