Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 806 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.4427. Min Act: -0.1700
Data Index: 2623042 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.3489. Min Act: -0.1700
Data Index: 382379 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.3177. Min Act: -0.1700
Data Index: 7152530 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2864. Min Act: -0.1700
Data Index: 3965496 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2552. Min Act: -0.1700
Data Index: 975244 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2864. Min Act: -0.1700
Data Index: 649234 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1927. Min Act: -0.1700
Data Index: 5552531 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.2239. Min Act: -0.1700
Data Index: 4466981 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1927. Min Act: -0.1700
Data Index: 6635784 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1614. Min Act: -0.1700
Data Index: 688466 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1302. Min Act: -0.1700
Data Index: 3051748 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1614. Min Act: -0.1700
Data Index: 6069693 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1614. Min Act: -0.1700
Data Index: 7888009 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1302. Min Act: -0.1700
Data Index: 2887017 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1302. Min Act: -0.1700
Data Index: 3382425 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1302. Min Act: -0.1700
Data Index: 981322 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1614. Min Act: -0.1700
Data Index: 2497319 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1302. Min Act: -0.1700
Data Index: 1559088 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.1302. Min Act: -0.1700
Data Index: 2939837 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4427. Min Range: -4.4427
Max Act: 4.0989. Min Act: -0.1700
Data Index: 3329489 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19