Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2361 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.5646. Min Act: -0.1700
Data Index: 7326186 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.5646. Min Act: -0.1700
Data Index: 8257012 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.2834. Min Act: -0.1700
Data Index: 4720581 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.2521. Min Act: -0.1700
Data Index: 7515238 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.1584. Min Act: -0.1700
Data Index: 6629498 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.1896. Min Act: -0.1700
Data Index: 2002610 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.1584. Min Act: -0.1700
Data Index: 122470 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.0959. Min Act: -0.1700
Data Index: 5001141 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.1271. Min Act: -0.1700
Data Index: 4218439 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.1271. Min Act: -0.1700
Data Index: 4328399 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.1271. Min Act: -0.1700
Data Index: 2352244 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.0959. Min Act: -0.1700
Data Index: 3430837 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.0646. Min Act: -0.1700
Data Index: 8458973 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.0646. Min Act: -0.1700
Data Index: 3123008 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.0334. Min Act: -0.1700
Data Index: 2080763 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.0334. Min Act: -0.1700
Data Index: 2457952 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.0334. Min Act: -0.1700
Data Index: 7443400 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5646. Min Range: -6.5646
Max Act: 5.9709. Min Act: -0.1700
Data Index: 1553284 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5646. Min Range: -6.5646
Max Act: 6.0021. Min Act: -0.1700
Data Index: 5791867 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5646. Min Range: -6.5646
Max Act: 5.9709. Min Act: -0.1700
Data Index: 6165492 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19