Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1284 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.6519. Min Act: -0.1700
Data Index: 2929816 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.7144. Min Act: -0.1700
Data Index: 599478 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.7144. Min Act: -0.1700
Data Index: 8484568 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.6519. Min Act: -0.1700
Data Index: 2698026 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.5582. Min Act: -0.1700
Data Index: 352313 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.5269. Min Act: -0.1700
Data Index: 5255511 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.5269. Min Act: -0.1700
Data Index: 5670984 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4957. Min Act: -0.1700
Data Index: 7263391 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4957. Min Act: -0.1700
Data Index: 5903274 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4957. Min Act: -0.1700
Data Index: 8176069 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4957. Min Act: -0.1700
Data Index: 4187401 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4644. Min Act: -0.1700
Data Index: 6750407 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4332. Min Act: -0.1700
Data Index: 4386727 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4332. Min Act: -0.1700
Data Index: 5198983 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4332. Min Act: -0.1700
Data Index: 6733302 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4332. Min Act: -0.1700
Data Index: 5017257 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4019. Min Act: -0.1700
Data Index: 1302265 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.4019. Min Act: -0.1700
Data Index: 3039155 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.3707. Min Act: -0.1700
Data Index: 3025483 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7144. Min Range: -7.7144
Max Act: 7.3707. Min Act: -0.1700
Data Index: 5142764 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19