Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4100. Min Range: -9.4100
Max Act: 9.4100. Min Act: -0.1700
Data Index: 7042039 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4100. Min Range: -9.4100
Max Act: 9.4100. Min Act: -0.1700
Data Index: 3032243 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4100. Min Range: -9.4100
Max Act: 9.1600. Min Act: -0.1700
Data Index: 7556176 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4100. Min Range: -9.4100
Max Act: 9.0975. Min Act: -0.1700
Data Index: 6335415 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4100. Min Range: -9.4100
Max Act: 9.0975. Min Act: -0.1700
Data Index: 6190975 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4100. Min Range: -9.4100
Max Act: 9.0350. Min Act: -0.1700
Data Index: 5189841 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4100. Min Range: -9.4100
Max Act: 9.0350. Min Act: -0.1700
Data Index: 3131138 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.9725. Min Act: -0.1700
Data Index: 1276617 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.9100. Min Act: -0.1700
Data Index: 549535 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.9725. Min Act: -0.1700
Data Index: 1371638 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.8475. Min Act: -0.1700
Data Index: 4429991 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.8475. Min Act: -0.1700
Data Index: 2675408 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.8475. Min Act: -0.1700
Data Index: 4396214 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.7850. Min Act: -0.1700
Data Index: 6671220 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.7850. Min Act: -0.1700
Data Index: 3378548 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.7225. Min Act: -0.1700
Data Index: 3756855 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.7850. Min Act: -0.1700
Data Index: 3430347 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.8475. Min Act: -0.1700
Data Index: 6197986 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.7850. Min Act: -0.1700
Data Index: 3771625 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4100. Min Range: -9.4100
Max Act: 8.7850. Min Act: -0.1700
Data Index: 474933 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19