Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 604 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1158. Min Range: -5.1158
Max Act: 5.1158. Min Act: -0.1700
Data Index: 4509740 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1158. Min Range: -5.1158
Max Act: 5.0220. Min Act: -0.1700
Data Index: 5346134 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8345. Min Act: -0.1700
Data Index: 34360 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8658. Min Act: -0.1700
Data Index: 7552292 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8033. Min Act: -0.1700
Data Index: 1977005 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8033. Min Act: -0.1700
Data Index: 1488378 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8033. Min Act: -0.1700
Data Index: 5573572 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8033. Min Act: -0.1700
Data Index: 3994129 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.8033. Min Act: -0.1700
Data Index: 8183790 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.7720. Min Act: -0.1700
Data Index: 3066751 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.7720. Min Act: -0.1700
Data Index: 6840130 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.7408. Min Act: -0.1700
Data Index: 7434696 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.7095. Min Act: -0.1700
Data Index: 1460302 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.7408. Min Act: -0.1700
Data Index: 6330133 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.7095. Min Act: -0.1700
Data Index: 4065863 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.7408. Min Act: -0.1700
Data Index: 1733024 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.7095. Min Act: -0.1700
Data Index: 6060324 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.7095. Min Act: -0.1700
Data Index: 5427856 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.7095. Min Act: -0.1700
Data Index: 3649165 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1158. Min Range: -5.1158
Max Act: 4.6783. Min Act: -0.1700
Data Index: 4649329 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19