Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 708 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5532. Min Range: -9.5532
Max Act: 9.5532. Min Act: -0.1700
Data Index: 306993 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5532. Min Range: -9.5532
Max Act: 9.4907. Min Act: -0.1700
Data Index: 3653347 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5532. Min Range: -9.5532
Max Act: 9.2407. Min Act: -0.1700
Data Index: 7845495 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.9282. Min Act: -0.1700
Data Index: 3320804 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.8657. Min Act: -0.1700
Data Index: 7081367 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.8032. Min Act: -0.1700
Data Index: 7208300 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.8032. Min Act: -0.1700
Data Index: 6940306 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.8032. Min Act: -0.1700
Data Index: 6167902 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.8032. Min Act: -0.1700
Data Index: 5979261 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.7407. Min Act: -0.1700
Data Index: 3548241 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.7407. Min Act: -0.1700
Data Index: 8731852 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.7407. Min Act: -0.1700
Data Index: 6034374 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.6782. Min Act: -0.1700
Data Index: 6373106 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.6782. Min Act: -0.1700
Data Index: 8117964 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.7407. Min Act: -0.1700
Data Index: 8198880 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.6157. Min Act: -0.1700
Data Index: 3849414 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.6157. Min Act: -0.1700
Data Index: 8231457 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.6157. Min Act: -0.1700
Data Index: 4377143 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.6157. Min Act: -0.1700
Data Index: 7020727 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5532. Min Range: -9.5532
Max Act: 8.5532. Min Act: -0.1700
Data Index: 3175657 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19