Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5614 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2201. Min Range: -7.2201
Max Act: 7.2201. Min Act: -0.1700
Data Index: 1424327 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2201. Min Range: -7.2201
Max Act: 7.1889. Min Act: -0.1700
Data Index: 3007041 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2201. Min Range: -7.2201
Max Act: 7.0639. Min Act: -0.1700
Data Index: 6329034 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2201. Min Range: -7.2201
Max Act: 7.0326. Min Act: -0.1700
Data Index: 3147751 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2201. Min Range: -7.2201
Max Act: 7.0326. Min Act: -0.1700
Data Index: 2798953 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2201. Min Range: -7.2201
Max Act: 7.0326. Min Act: -0.1700
Data Index: 2030890 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2201. Min Range: -7.2201
Max Act: 7.0014. Min Act: -0.1700
Data Index: 8181925 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.9389. Min Act: -0.1700
Data Index: 1648481 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.9389. Min Act: -0.1700
Data Index: 407730 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.9389. Min Act: -0.1700
Data Index: 2265027 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.9076. Min Act: -0.1700
Data Index: 3566184 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.9076. Min Act: -0.1700
Data Index: 6632319 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.9076. Min Act: -0.1700
Data Index: 5425923 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.9076. Min Act: -0.1700
Data Index: 5411778 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.8451. Min Act: -0.1700
Data Index: 4475364 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.8139. Min Act: -0.1700
Data Index: 6298606 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.7826. Min Act: -0.1700
Data Index: 6364960 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.8139. Min Act: -0.1700
Data Index: 5630022 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.7514. Min Act: -0.1700
Data Index: 287577 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2201. Min Range: -7.2201
Max Act: 6.7514. Min Act: -0.1700
Data Index: 4204518 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19