Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1508 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.6172. Min Act: -0.1700
Data Index: 278867 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.5528. Min Act: -0.1700
Data Index: 7394106 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.5042. Min Act: -0.1700
Data Index: 7704214 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.5204. Min Act: -0.1700
Data Index: 8783314 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.5204. Min Act: -0.1700
Data Index: 1607755 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.5042. Min Act: -0.1700
Data Index: 2809604 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4880. Min Act: -0.1700
Data Index: 6510116 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4393. Min Act: -0.1700
Data Index: 7509941 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4393. Min Act: -0.1700
Data Index: 6472219 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4393. Min Act: -0.1700
Data Index: 361688 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4556. Min Act: -0.1700
Data Index: 2649929 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4556. Min Act: -0.1700
Data Index: 7856315 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4230. Min Act: -0.1700
Data Index: 2318261 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4393. Min Act: -0.1700
Data Index: 5162875 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4230. Min Act: -0.1700
Data Index: 2472329 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4230. Min Act: -0.1700
Data Index: 7119553 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4230. Min Act: -0.1700
Data Index: 485294 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4230. Min Act: -0.1700
Data Index: 1819889 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4067. Min Act: -0.1700
Data Index: 5669101 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6172. Min Range: -2.6172
Max Act: 2.4230. Min Act: -0.1700
Data Index: 5756944 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19