Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6885. Min Range: -5.6885
Max Act: 5.6885. Min Act: -0.1700
Data Index: 5770928 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6885. Min Range: -5.6885
Max Act: 5.0635. Min Act: -0.1700
Data Index: 4930541 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6885. Min Range: -5.6885
Max Act: 5.0010. Min Act: -0.1700
Data Index: 7625571 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.9385. Min Act: -0.1700
Data Index: 803760 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.9073. Min Act: -0.1700
Data Index: 5686792 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.9073. Min Act: -0.1700
Data Index: 852969 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.9073. Min Act: -0.1700
Data Index: 745922 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.8135. Min Act: -0.1700
Data Index: 5327847 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.8448. Min Act: -0.1700
Data Index: 3733966 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.8448. Min Act: -0.1700
Data Index: 1242219 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.8448. Min Act: -0.1700
Data Index: 502154 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.8448. Min Act: -0.1700
Data Index: 4750122 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.8135. Min Act: -0.1700
Data Index: 7661436 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.8135. Min Act: -0.1700
Data Index: 902587 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.8135. Min Act: -0.1700
Data Index: 409065 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.8135. Min Act: -0.1700
Data Index: 966911 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.8135. Min Act: -0.1700
Data Index: 1242220 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.7823. Min Act: -0.1700
Data Index: 4494358 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.7823. Min Act: -0.1700
Data Index: 460176 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6885. Min Range: -5.6885
Max Act: 4.7823. Min Act: -0.1700
Data Index: 7461333 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19