Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4408 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1461. Min Range: -6.1461
Max Act: 6.1461. Min Act: -0.1700
Data Index: 3345445 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1461. Min Range: -6.1461
Max Act: 6.0523. Min Act: -0.1700
Data Index: 7721518 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.9273. Min Act: -0.1700
Data Index: 7358833 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.8648. Min Act: -0.1700
Data Index: 3198707 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.8336. Min Act: -0.1700
Data Index: 7711010 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.8023. Min Act: -0.1700
Data Index: 6593185 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.8023. Min Act: -0.1700
Data Index: 5897732 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.7398. Min Act: -0.1700
Data Index: 5480123 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.7086. Min Act: -0.1700
Data Index: 3156354 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.7086. Min Act: -0.1700
Data Index: 3862004 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.6773. Min Act: -0.1700
Data Index: 8088831 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.6773. Min Act: -0.1700
Data Index: 4076724 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.6461. Min Act: -0.1700
Data Index: 2447670 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.6148. Min Act: -0.1700
Data Index: 2527976 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.6148. Min Act: -0.1700
Data Index: 4504865 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.6148. Min Act: -0.1700
Data Index: 2950548 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.6148. Min Act: -0.1700
Data Index: 4610935 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.5836. Min Act: -0.1700
Data Index: 1459874 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.5836. Min Act: -0.1700
Data Index: 1022766 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1461. Min Range: -6.1461
Max Act: 5.6148. Min Act: -0.1700
Data Index: 340309 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19