Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 354 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.4304. Min Act: -0.1700
Data Index: 4240175 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.3054. Min Act: -0.1700
Data Index: 7287560 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.3054. Min Act: -0.1700
Data Index: 1847016 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.2741. Min Act: -0.1700
Data Index: 6663155 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.2741. Min Act: -0.1700
Data Index: 2107122 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.2429. Min Act: -0.1700
Data Index: 2303173 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.2116. Min Act: -0.1700
Data Index: 3186792 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.2116. Min Act: -0.1700
Data Index: 4421202 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1804. Min Act: -0.1700
Data Index: 1879082 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1804. Min Act: -0.1700
Data Index: 8691487 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1491. Min Act: -0.1700
Data Index: 6541596 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1491. Min Act: -0.1700
Data Index: 635741 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1179. Min Act: -0.1700
Data Index: 2365404 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1804. Min Act: -0.1700
Data Index: 1709807 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1491. Min Act: -0.1700
Data Index: 492677 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1491. Min Act: -0.1700
Data Index: 3938893 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1491. Min Act: -0.1700
Data Index: 6366044 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1804. Min Act: -0.1700
Data Index: 6356591 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1179. Min Act: -0.1700
Data Index: 4582407 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4304. Min Range: -4.4304
Max Act: 4.1491. Min Act: -0.1700
Data Index: 4489728 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19