Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1528 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.5247. Min Act: -0.1700
Data Index: 1452357 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.5072. Min Act: -0.1700
Data Index: 6795639 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4896. Min Act: -0.1700
Data Index: 2941678 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4720. Min Act: -0.1697
Data Index: 7669430 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4720. Min Act: -0.1699
Data Index: 4233987 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4720. Min Act: -0.1686
Data Index: 7721299 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4544. Min Act: -0.1700
Data Index: 5393231 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4544. Min Act: -0.1700
Data Index: 8094840 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4280. Min Act: -0.1700
Data Index: 8536248 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4368. Min Act: -0.1700
Data Index: 5675294 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4280. Min Act: -0.1700
Data Index: 3831244 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4456. Min Act: -0.1700
Data Index: 2429723 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4280. Min Act: -0.1700
Data Index: 7985804 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4280. Min Act: -0.1700
Data Index: 796911 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4192. Min Act: -0.1700
Data Index: 119071 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4280. Min Act: -0.1700
Data Index: 3643977 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4280. Min Act: -0.1700
Data Index: 515804 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4192. Min Act: -0.1700
Data Index: 1193198 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4192. Min Act: -0.1700
Data Index: 3503210 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5247. Min Range: -1.5247
Max Act: 1.4192. Min Act: -0.1700
Data Index: 7485314 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19