Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3402 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.1169. Min Range: -15.1169
Max Act: 15.1169. Min Act: -0.1700
Data Index: 3541596 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.1169. Min Range: -15.1169
Max Act: 15.0544. Min Act: -0.1700
Data Index: 1522669 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.9919. Min Act: -0.1700
Data Index: 2339499 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.9919. Min Act: -0.1700
Data Index: 4005763 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.9919. Min Act: -0.1700
Data Index: 1522670 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.8669. Min Act: -0.1700
Data Index: 2212376 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.9294. Min Act: -0.1700
Data Index: 8270310 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.9919. Min Act: -0.1700
Data Index: 3357998 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.8669. Min Act: -0.1700
Data Index: 3468776 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.9294. Min Act: -0.1699
Data Index: 4991945 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.8669. Min Act: -0.1700
Data Index: 3227843 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.7419. Min Act: -0.1700
Data Index: 5881872 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.7419. Min Act: -0.1700
Data Index: 4984805 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.6169. Min Act: -0.1700
Data Index: 3227840 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.4294. Min Act: -0.1700
Data Index: 6857551 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.4294. Min Act: -0.1700
Data Index: 6779543 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.3044. Min Act: -0.1700
Data Index: 1177586 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.3669. Min Act: -0.1700
Data Index: 478218 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.3044. Min Act: -0.1700
Data Index: 5006716 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.1169. Min Range: -15.1169
Max Act: 14.3669. Min Act: -0.1700
Data Index: 2014155 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19