Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3918 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.9004. Min Act: -0.1700
Data Index: 430405 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.7442. Min Act: -0.1700
Data Index: 7980091 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.7442. Min Act: -0.1700
Data Index: 8721386 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.7129. Min Act: -0.1700
Data Index: 6161245 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.6504. Min Act: -0.1700
Data Index: 770363 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.6192. Min Act: -0.1700
Data Index: 3196524 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.6192. Min Act: -0.1700
Data Index: 1261860 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.6192. Min Act: -0.1700
Data Index: 8067572 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.5879. Min Act: -0.1700
Data Index: 6807698 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.5254. Min Act: -0.1700
Data Index: 3740829 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.4942. Min Act: -0.1700
Data Index: 5964988 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.4317. Min Act: -0.1700
Data Index: 6027085 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.4629. Min Act: -0.1700
Data Index: 2412629 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.4942. Min Act: -0.1700
Data Index: 1766604 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.4629. Min Act: -0.1700
Data Index: 3092961 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.4942. Min Act: -0.1700
Data Index: 893102 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.4004. Min Act: -0.1700
Data Index: 1971639 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.4317. Min Act: -0.1700
Data Index: 5117718 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.3692. Min Act: -0.1700
Data Index: 5616732 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9004. Min Range: -6.9004
Max Act: 6.4317. Min Act: -0.1700
Data Index: 4613849 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19