Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1509 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2481. Min Range: -8.2481
Max Act: 8.2481. Min Act: -0.1700
Data Index: 5533257 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2481. Min Range: -8.2481
Max Act: 8.1231. Min Act: -0.1700
Data Index: 8355405 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2481. Min Range: -8.2481
Max Act: 8.1856. Min Act: -0.1700
Data Index: 4244179 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2481. Min Range: -8.2481
Max Act: 8.0606. Min Act: -0.1700
Data Index: 7522772 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.8731. Min Act: -0.1700
Data Index: 2725473 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.8418. Min Act: -0.1700
Data Index: 8704951 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.8106. Min Act: -0.1700
Data Index: 8177423 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.8106. Min Act: -0.1700
Data Index: 548114 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.7793. Min Act: -0.1700
Data Index: 3813777 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.8106. Min Act: -0.1700
Data Index: 1951879 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.7481. Min Act: -0.1700
Data Index: 8366341 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.7168. Min Act: -0.1700
Data Index: 4205046 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.7793. Min Act: -0.1700
Data Index: 4143767 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.7168. Min Act: -0.1700
Data Index: 3482717 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.7168. Min Act: -0.1700
Data Index: 8120024 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.7168. Min Act: -0.1700
Data Index: 2318322 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.7168. Min Act: -0.1700
Data Index: 4713207 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.7168. Min Act: -0.1700
Data Index: 8511784 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.6543. Min Act: -0.1700
Data Index: 7472665 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2481. Min Range: -8.2481
Max Act: 7.6856. Min Act: -0.1700
Data Index: 3147834 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19