Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5496 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.8259. Min Act: -0.1700
Data Index: 396682 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.7946. Min Act: -0.1700
Data Index: 2083086 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.7946. Min Act: -0.1700
Data Index: 4570521 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.7946. Min Act: -0.1700
Data Index: 6672243 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.7321. Min Act: -0.1700
Data Index: 8633135 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.7009. Min Act: -0.1700
Data Index: 3516353 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.6696. Min Act: -0.1700
Data Index: 1451419 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.6696. Min Act: -0.1700
Data Index: 2759269 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.6071. Min Act: -0.1700
Data Index: 2858481 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.6071. Min Act: -0.1700
Data Index: 2091686 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.6071. Min Act: -0.1700
Data Index: 1861504 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.6071. Min Act: -0.1700
Data Index: 6229736 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.5759. Min Act: -0.1700
Data Index: 3066638 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.6071. Min Act: -0.1700
Data Index: 6136035 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.5759. Min Act: -0.1700
Data Index: 461117 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.5134. Min Act: -0.1700
Data Index: 7592451 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.5446. Min Act: -0.1700
Data Index: 5613063 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.5446. Min Act: -0.1700
Data Index: 7010723 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.5134. Min Act: -0.1700
Data Index: 4745932 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8259. Min Range: -5.8259
Max Act: 5.5446. Min Act: -0.1700
Data Index: 4085811 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19