Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4103 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.8163. Min Act: -0.1700
Data Index: 8101359 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.5975. Min Act: -0.1700
Data Index: 3587514 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.5663. Min Act: -0.1700
Data Index: 5684010 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.4725. Min Act: -0.1700
Data Index: 1629213 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.5037. Min Act: -0.1700
Data Index: 3484489 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.5037. Min Act: -0.1700
Data Index: 6199823 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.5350. Min Act: -0.1700
Data Index: 6120355 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.4725. Min Act: -0.1700
Data Index: 1742243 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.4725. Min Act: -0.1700
Data Index: 3459581 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.4412. Min Act: -0.1700
Data Index: 7435338 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.4412. Min Act: -0.1700
Data Index: 424910 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.4412. Min Act: -0.1700
Data Index: 171034 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.4100. Min Act: -0.1700
Data Index: 4589695 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.4412. Min Act: -0.1700
Data Index: 3430495 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.3787. Min Act: -0.1700
Data Index: 2042613 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.4100. Min Act: -0.1700
Data Index: 3763776 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.3787. Min Act: -0.1700
Data Index: 488949 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.3475. Min Act: -0.1700
Data Index: 4623984 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.3787. Min Act: -0.1700
Data Index: 6199826 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8163. Min Range: -4.8163
Max Act: 4.3787. Min Act: -0.1700
Data Index: 805758 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19