Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3406 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.8880. Min Act: -0.1700
Data Index: 5484274 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.8880. Min Act: -0.1700
Data Index: 2738840 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.8255. Min Act: -0.1700
Data Index: 4228276 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.8567. Min Act: -0.1700
Data Index: 3921674 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.7942. Min Act: -0.1700
Data Index: 5170856 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.7942. Min Act: -0.1700
Data Index: 5973699 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.7005. Min Act: -0.1700
Data Index: 3137746 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.7317. Min Act: -0.1700
Data Index: 11120 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.6692. Min Act: -0.1700
Data Index: 6704838 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.6380. Min Act: -0.1700
Data Index: 2504824 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.5755. Min Act: -0.1700
Data Index: 6098433 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.6380. Min Act: -0.1700
Data Index: 7850141 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.6067. Min Act: -0.1700
Data Index: 6348530 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.5442. Min Act: -0.1700
Data Index: 3242253 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.5442. Min Act: -0.1700
Data Index: 7267662 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.5130. Min Act: -0.1700
Data Index: 8007460 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.5130. Min Act: -0.1700
Data Index: 742189 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.4817. Min Act: -0.1700
Data Index: 444327 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.4817. Min Act: -0.1700
Data Index: 8514694 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8880. Min Range: -6.8880
Max Act: 6.4505. Min Act: -0.1700
Data Index: 4678353 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #19