Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1822 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1720. Min Range: -7.1720
Max Act: 7.1720. Min Act: -0.1700
Data Index: 3051206 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.8595. Min Act: -0.1700
Data Index: 5636649 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.8283. Min Act: -0.1700
Data Index: 1828834 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.6720. Min Act: -0.1700
Data Index: 1315345 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.6095. Min Act: -0.1700
Data Index: 8533644 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.6720. Min Act: -0.1700
Data Index: 2658660 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.6095. Min Act: -0.1700
Data Index: 1630625 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.6408. Min Act: -0.1700
Data Index: 6443390 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.5783. Min Act: -0.1700
Data Index: 2117364 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.5783. Min Act: -0.1700
Data Index: 7941869 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.5783. Min Act: -0.1700
Data Index: 6443393 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.5158. Min Act: -0.1700
Data Index: 5627152 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.5158. Min Act: -0.1700
Data Index: 7198142 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.5470. Min Act: -0.1700
Data Index: 2475003 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.5158. Min Act: -0.1700
Data Index: 6443394 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.4533. Min Act: -0.1700
Data Index: 3623354 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.4220. Min Act: -0.1697
Data Index: 6443392 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.3908. Min Act: -0.1700
Data Index: 184396 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.3908. Min Act: -0.1700
Data Index: 4619304 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1720. Min Range: -7.1720
Max Act: 6.4220. Min Act: -0.1700
Data Index: 2253216 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #19