Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1377. Min Range: -6.1377
Max Act: 6.1377. Min Act: -0.1700
Data Index: 1208310 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1377. Min Range: -6.1377
Max Act: 6.1065. Min Act: -0.1700
Data Index: 1570453 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1377. Min Range: -6.1377
Max Act: 6.1065. Min Act: -0.1700
Data Index: 1142985 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1377. Min Range: -6.1377
Max Act: 6.0752. Min Act: -0.1700
Data Index: 4156426 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1377. Min Range: -6.1377
Max Act: 6.1065. Min Act: -0.1700
Data Index: 2590585 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1377. Min Range: -6.1377
Max Act: 6.0440. Min Act: -0.1700
Data Index: 4122581 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1377. Min Range: -6.1377
Max Act: 6.0440. Min Act: -0.1699
Data Index: 3839871 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9815. Min Act: -0.1700
Data Index: 6963112 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1377. Min Range: -6.1377
Max Act: 6.0127. Min Act: -0.1700
Data Index: 552594 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9815. Min Act: -0.1700
Data Index: 6395767 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9815. Min Act: -0.1700
Data Index: 6390478 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9502. Min Act: -0.1700
Data Index: 7488446 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9502. Min Act: -0.1700
Data Index: 8633973 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9502. Min Act: -0.1700
Data Index: 569563 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9502. Min Act: -0.1700
Data Index: 448996 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9190. Min Act: -0.1700
Data Index: 569562 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9502. Min Act: -0.1700
Data Index: 1308189 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9502. Min Act: -0.1700
Data Index: 315152 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9190. Min Act: -0.1700
Data Index: 1516539 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1377. Min Range: -6.1377
Max Act: 5.9190. Min Act: -0.1700
Data Index: 2711080 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19