Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1669 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.6304. Min Act: -0.1700
Data Index: 789850 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4116. Min Act: -0.1700
Data Index: 8078480 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.4116. Min Act: -0.1700
Data Index: 77351 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3804. Min Act: -0.1700
Data Index: 6973559 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3804. Min Act: -0.1700
Data Index: 4564606 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3804. Min Act: -0.1700
Data Index: 8012904 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 8078476 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3491. Min Act: -0.1700
Data Index: 6980562 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2866. Min Act: -0.1700
Data Index: 447917 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3179. Min Act: -0.1700
Data Index: 8078473 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.3179. Min Act: -0.1700
Data Index: 6253600 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2866. Min Act: -0.1700
Data Index: 1219369 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2554. Min Act: -0.1700
Data Index: 2052730 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2866. Min Act: -0.1700
Data Index: 2396458 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2554. Min Act: -0.1700
Data Index: 7349102 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2554. Min Act: -0.1700
Data Index: 4932203 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2554. Min Act: -0.1700
Data Index: 7644285 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2241. Min Act: -0.1700
Data Index: 2551426 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2554. Min Act: -0.1700
Data Index: 6499313 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6304. Min Range: -4.6304
Max Act: 4.2241. Min Act: -0.1700
Data Index: 7490120 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19