Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4230 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3095. Min Range: -7.3095
Max Act: 7.3095. Min Act: -0.1700
Data Index: 1402300 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3095. Min Range: -7.3095
Max Act: 7.2470. Min Act: -0.1700
Data Index: 2441803 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3095. Min Range: -7.3095
Max Act: 7.2157. Min Act: -0.1700
Data Index: 8548246 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3095. Min Range: -7.3095
Max Act: 7.1532. Min Act: -0.1700
Data Index: 6104897 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3095. Min Range: -7.3095
Max Act: 7.1220. Min Act: -0.1700
Data Index: 7835960 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3095. Min Range: -7.3095
Max Act: 7.1220. Min Act: -0.1700
Data Index: 1349348 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3095. Min Range: -7.3095
Max Act: 7.0282. Min Act: -0.1700
Data Index: 1779773 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3095. Min Range: -7.3095
Max Act: 7.0282. Min Act: -0.1700
Data Index: 1579187 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3095. Min Range: -7.3095
Max Act: 7.0282. Min Act: -0.1700
Data Index: 8671152 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.9970. Min Act: -0.1700
Data Index: 306553 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.9657. Min Act: -0.1700
Data Index: 2067705 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.9032. Min Act: -0.1700
Data Index: 2362809 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.9345. Min Act: -0.1700
Data Index: 6767275 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.8720. Min Act: -0.1700
Data Index: 10695 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.9032. Min Act: -0.1700
Data Index: 7784511 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.8720. Min Act: -0.1700
Data Index: 4657977 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.8720. Min Act: -0.1700
Data Index: 1897691 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.8407. Min Act: -0.1700
Data Index: 4990560 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.8095. Min Act: -0.1700
Data Index: 4515145 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3095. Min Range: -7.3095
Max Act: 6.7782. Min Act: -0.1700
Data Index: 6526479 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19