Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1933 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.9535. Min Act: -0.1700
Data Index: 3823290 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.8910. Min Act: -0.1700
Data Index: 6175018 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.8285. Min Act: -0.1700
Data Index: 2863812 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.8285. Min Act: -0.1700
Data Index: 7929120 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.8285. Min Act: -0.1700
Data Index: 1736468 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7973. Min Act: -0.1700
Data Index: 8613050 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7973. Min Act: -0.1700
Data Index: 1541486 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7973. Min Act: -0.1700
Data Index: 1627721 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7660. Min Act: -0.1700
Data Index: 7491755 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7660. Min Act: -0.1700
Data Index: 4300344 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7660. Min Act: -0.1700
Data Index: 5334470 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7660. Min Act: -0.1700
Data Index: 1422318 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7660. Min Act: -0.1700
Data Index: 2380788 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7660. Min Act: -0.1700
Data Index: 4089399 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7660. Min Act: -0.1700
Data Index: 4809462 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7348. Min Act: -0.1700
Data Index: 5369727 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7348. Min Act: -0.1700
Data Index: 5812347 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7660. Min Act: -0.1700
Data Index: 1637543 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7348. Min Act: -0.1700
Data Index: 5837631 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9535. Min Range: -6.9535
Max Act: 6.7348. Min Act: -0.1700
Data Index: 5261918 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19