Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3173 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.6481. Min Act: -0.1700
Data Index: 8101099 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.5856. Min Act: -0.1700
Data Index: 1336773 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.5856. Min Act: -0.1700
Data Index: 6117669 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.5231. Min Act: -0.1700
Data Index: 2595777 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.4919. Min Act: -0.1700
Data Index: 4103460 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.4606. Min Act: -0.1700
Data Index: 7145388 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.3981. Min Act: -0.1700
Data Index: 7818307 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.3981. Min Act: -0.1700
Data Index: 6330040 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.3356. Min Act: -0.1700
Data Index: 5766992 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.3356. Min Act: -0.1700
Data Index: 3019633 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.3981. Min Act: -0.1700
Data Index: 2071519 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.3669. Min Act: -0.1700
Data Index: 1358103 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.3044. Min Act: -0.1700
Data Index: 2216620 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.2731. Min Act: -0.1700
Data Index: 1622315 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.3044. Min Act: -0.1700
Data Index: 5967825 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.2731. Min Act: -0.1700
Data Index: 3361310 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.2419. Min Act: -0.1700
Data Index: 5485876 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.2419. Min Act: -0.1700
Data Index: 7453598 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.2106. Min Act: -0.1700
Data Index: 5653645 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6481. Min Range: -4.6481
Max Act: 4.2419. Min Act: -0.1700
Data Index: 15321 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #19