Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 460 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.2355. Min Act: -0.1699
Data Index: 89218 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.2190. Min Act: -0.1700
Data Index: 1097743 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1858. Min Act: -0.1700
Data Index: 6026226 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.2024. Min Act: -0.1700
Data Index: 391702 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1858. Min Act: -0.1700
Data Index: 8762746 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1691. Min Act: -0.1700
Data Index: 6770505 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1858. Min Act: -0.1700
Data Index: 6925604 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1691. Min Act: -0.1700
Data Index: 3012510 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1525. Min Act: -0.1700
Data Index: 255837 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1525. Min Act: -0.1699
Data Index: 6426069 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1525. Min Act: -0.1700
Data Index: 4718137 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1525. Min Act: -0.1700
Data Index: 6058876 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1525. Min Act: -0.1700
Data Index: 5487260 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1358. Min Act: -0.1700
Data Index: 2019973 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1358. Min Act: -0.1700
Data Index: 7454924 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1358. Min Act: -0.1700
Data Index: 753358 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1358. Min Act: -0.1700
Data Index: 1284892 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1191. Min Act: -0.1700
Data Index: 451924 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1191. Min Act: -0.1700
Data Index: 6731579 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2355. Min Range: -2.2355
Max Act: 2.1358. Min Act: -0.1700
Data Index: 3358680 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19