Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 681 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.1157. Min Range: -9.1157
Max Act: 9.1157. Min Act: -0.1700
Data Index: 4050295 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1157. Min Range: -9.1157
Max Act: 9.0532. Min Act: -0.1700
Data Index: 761387 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1157. Min Range: -9.1157
Max Act: 9.0532. Min Act: -0.1700
Data Index: 7002941 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.9282. Min Act: -0.1700
Data Index: 5812462 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.8657. Min Act: -0.1700
Data Index: 8422672 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.9282. Min Act: -0.1700
Data Index: 7695955 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.8657. Min Act: -0.1700
Data Index: 5812467 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.8657. Min Act: -0.1700
Data Index: 5812470 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.8032. Min Act: -0.1700
Data Index: 4775317 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.8032. Min Act: -0.1700
Data Index: 5812463 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.8032. Min Act: -0.1700
Data Index: 5812457 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.8657. Min Act: -0.1700
Data Index: 5889102 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.7407. Min Act: -0.1700
Data Index: 5812473 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.7407. Min Act: -0.1700
Data Index: 5812472 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.6782. Min Act: -0.1700
Data Index: 1144424 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.7407. Min Act: -0.1700
Data Index: 7673489 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.7407. Min Act: -0.1700
Data Index: 5812458 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.6782. Min Act: -0.1700
Data Index: 7375445 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.6157. Min Act: -0.1700
Data Index: 5812465 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1157. Min Range: -9.1157
Max Act: 8.6782. Min Act: -0.1700
Data Index: 5812468 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19