Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5324 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6606. Min Range: -7.6606
Max Act: 7.6606. Min Act: -0.1700
Data Index: 4610023 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6606. Min Range: -7.6606
Max Act: 7.0356. Min Act: -0.1700
Data Index: 3133766 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.8481. Min Act: -0.1700
Data Index: 5967006 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.7856. Min Act: -0.1700
Data Index: 6618804 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.7231. Min Act: -0.1700
Data Index: 6321706 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.6919. Min Act: -0.1700
Data Index: 5718592 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.6919. Min Act: -0.1700
Data Index: 3971869 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.6294. Min Act: -0.1700
Data Index: 7841357 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.6294. Min Act: -0.1700
Data Index: 5964468 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.5981. Min Act: -0.1700
Data Index: 2659873 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.5669. Min Act: -0.1700
Data Index: 5890081 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.5669. Min Act: -0.1700
Data Index: 6566236 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.5981. Min Act: -0.1700
Data Index: 7221482 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.5356. Min Act: -0.1700
Data Index: 3419834 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.5669. Min Act: -0.1700
Data Index: 5349399 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.5356. Min Act: -0.1700
Data Index: 3353813 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.5669. Min Act: -0.1700
Data Index: 7926529 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.5044. Min Act: -0.1700
Data Index: 7538127 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.5044. Min Act: -0.1700
Data Index: 915313 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6606. Min Range: -7.6606
Max Act: 6.4731. Min Act: -0.1700
Data Index: 5507523 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19