Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.7610. Min Range: -16.7610
Max Act: 16.7610. Min Act: -0.1700
Data Index: 2194104 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.7610. Min Range: -16.7610
Max Act: 16.6360. Min Act: -0.1700
Data Index: 5478688 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.7610. Min Range: -16.7610
Max Act: 16.5110. Min Act: -0.1700
Data Index: 8413490 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.7610. Min Range: -16.7610
Max Act: 16.1360. Min Act: -0.1700
Data Index: 1325864 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.7610. Min Range: -16.7610
Max Act: 16.2610. Min Act: -0.1699
Data Index: 1856788 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.7610. Min Range: -16.7610
Max Act: 16.1360. Min Act: -0.1700
Data Index: 4129790 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.7610. Min Range: -16.7610
Max Act: 16.0110. Min Act: -0.1698
Data Index: 586477 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.7610. Min Range: -16.7610
Max Act: 16.0110. Min Act: -0.1700
Data Index: 4434897 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.8860. Min Act: -0.1700
Data Index: 5710860 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.8860. Min Act: -0.1700
Data Index: 46194 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.8860. Min Act: -0.1700
Data Index: 2111942 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.8235. Min Act: -0.1700
Data Index: 5596224 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.8235. Min Act: -0.1700
Data Index: 6849661 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.7610. Min Act: -0.1700
Data Index: 397458 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.7610. Min Act: -0.1700
Data Index: 220081 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.6985. Min Act: -0.1700
Data Index: 1950427 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.7610. Min Act: -0.1700
Data Index: 5046931 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.7610. Min Act: -0.1700
Data Index: 3162466 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.7610. Min Act: -0.1700
Data Index: 910714 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.7610. Min Range: -16.7610
Max Act: 15.6985. Min Act: -0.1700
Data Index: 8589870 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19