Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1825 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.6282. Min Act: -0.1700
Data Index: 4788872 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.6282. Min Act: -0.1700
Data Index: 3809839 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.5657. Min Act: -0.1700
Data Index: 5517069 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.4095. Min Act: -0.1700
Data Index: 2848435 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3782. Min Act: -0.1700
Data Index: 423243 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3782. Min Act: -0.1700
Data Index: 8677945 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3782. Min Act: -0.1700
Data Index: 3074434 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3157. Min Act: -0.1700
Data Index: 59332 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3470. Min Act: -0.1700
Data Index: 3143701 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3470. Min Act: -0.1700
Data Index: 1262881 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3157. Min Act: -0.1700
Data Index: 3348251 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3470. Min Act: -0.1700
Data Index: 2662515 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3157. Min Act: -0.1700
Data Index: 6336061 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2845. Min Act: -0.1700
Data Index: 3046018 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2845. Min Act: -0.1700
Data Index: 11626 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.3157. Min Act: -0.1700
Data Index: 1578533 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2845. Min Act: -0.1700
Data Index: 7538890 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2845. Min Act: -0.1700
Data Index: 2504975 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2532. Min Act: -0.1700
Data Index: 1735661 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6282. Min Range: -5.6282
Max Act: 5.2220. Min Act: -0.1700
Data Index: 7375568 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19