Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3593 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.4476. Min Act: -0.1700
Data Index: 5120253 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.3226. Min Act: -0.1700
Data Index: 1889130 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.3226. Min Act: -0.1700
Data Index: 6724931 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.2600. Min Act: -0.1700
Data Index: 5205739 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.2600. Min Act: -0.1700
Data Index: 1924727 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.2288. Min Act: -0.1700
Data Index: 4319652 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.2288. Min Act: -0.1700
Data Index: 247539 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.2288. Min Act: -0.1700
Data Index: 5838164 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.2288. Min Act: -0.1700
Data Index: 5017988 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.1975. Min Act: -0.1700
Data Index: 2443374 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.1663. Min Act: -0.1700
Data Index: 5263058 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.1975. Min Act: -0.1700
Data Index: 978257 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.1038. Min Act: -0.1700
Data Index: 7908667 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.1038. Min Act: -0.1700
Data Index: 401407 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.1350. Min Act: -0.1700
Data Index: 7751906 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.1350. Min Act: -0.1700
Data Index: 313266 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.1350. Min Act: -0.1700
Data Index: 1969699 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.1038. Min Act: -0.1700
Data Index: 661917 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.1038. Min Act: -0.1700
Data Index: 7961573 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4476. Min Range: -4.4476
Max Act: 4.0725. Min Act: -0.1700
Data Index: 3652916 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #19