Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5912 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.8630. Min Act: -0.1700
Data Index: 46500 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.6755. Min Act: -0.1700
Data Index: 7997997 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.5817. Min Act: -0.1700
Data Index: 362204 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.5817. Min Act: -0.1700
Data Index: 6263786 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.5192. Min Act: -0.1700
Data Index: 1763943 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.5192. Min Act: -0.1700
Data Index: 8537852 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.4255. Min Act: -0.1700
Data Index: 1881470 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.3942. Min Act: -0.1700
Data Index: 8187594 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.3317. Min Act: -0.1700
Data Index: 2822829 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.3630. Min Act: -0.1700
Data Index: 5323651 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.3005. Min Act: -0.1700
Data Index: 7430260 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.2692. Min Act: -0.1700
Data Index: 5132550 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.2380. Min Act: -0.1700
Data Index: 4620346 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.2067. Min Act: -0.1700
Data Index: 5397171 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.2067. Min Act: -0.1700
Data Index: 1279363 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.1755. Min Act: -0.1700
Data Index: 4473314 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.1755. Min Act: -0.1700
Data Index: 6614210 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.1755. Min Act: -0.1700
Data Index: 4388318 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.1442. Min Act: -0.1700
Data Index: 47424 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8630. Min Range: -6.8630
Max Act: 6.1755. Min Act: -0.1700
Data Index: 2462522 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19