Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3420 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.4174. Min Range: -15.4174
Max Act: 15.4174. Min Act: -0.1700
Data Index: 8503732 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.4174. Min Range: -15.4174
Max Act: 15.1674. Min Act: -0.1700
Data Index: 920114 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.4174. Min Range: -15.4174
Max Act: 15.1674. Min Act: -0.1700
Data Index: 1940476 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.4174. Min Range: -15.4174
Max Act: 15.1049. Min Act: -0.1700
Data Index: 2114137 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.4174. Min Range: -15.4174
Max Act: 15.0424. Min Act: -0.1700
Data Index: 3040920 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.9799. Min Act: -0.1700
Data Index: 5167629 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.9799. Min Act: -0.1700
Data Index: 5796459 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.9799. Min Act: -0.1700
Data Index: 1892099 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.9174. Min Act: -0.1700
Data Index: 4666596 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.9174. Min Act: -0.1700
Data Index: 291010 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.8549. Min Act: -0.1700
Data Index: 725861 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.7924. Min Act: -0.1700
Data Index: 6764097 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.7924. Min Act: -0.1700
Data Index: 7699460 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.7299. Min Act: -0.1700
Data Index: 2958934 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.7299. Min Act: -0.1700
Data Index: 8800247 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.7299. Min Act: -0.1700
Data Index: 4295042 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.7299. Min Act: -0.1700
Data Index: 4060969 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.7299. Min Act: -0.1700
Data Index: 7490948 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.6674. Min Act: -0.1700
Data Index: 7157024 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.4174. Min Range: -15.4174
Max Act: 14.6674. Min Act: -0.1700
Data Index: 4395201 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #19