Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3016 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4898. Min Range: -9.4898
Max Act: 9.4898. Min Act: -0.1700
Data Index: 6251798 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4898. Min Range: -9.4898
Max Act: 9.2398. Min Act: -0.1700
Data Index: 6060760 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.9898. Min Act: -0.1700
Data Index: 5008767 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4898. Min Range: -9.4898
Max Act: 9.0523. Min Act: -0.1700
Data Index: 1719526 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.9898. Min Act: -0.1700
Data Index: 4718408 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.8648. Min Act: -0.1700
Data Index: 4292600 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.8648. Min Act: -0.1700
Data Index: 5008760 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.8648. Min Act: -0.1700
Data Index: 1858791 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.8023. Min Act: -0.1700
Data Index: 4755464 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.8648. Min Act: -0.1700
Data Index: 6797104 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.8648. Min Act: -0.1700
Data Index: 6199251 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.8023. Min Act: -0.1700
Data Index: 2528224 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.7398. Min Act: -0.1700
Data Index: 8502554 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.7398. Min Act: -0.1700
Data Index: 8021824 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.6773. Min Act: -0.1700
Data Index: 5445763 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.6773. Min Act: -0.1700
Data Index: 7985226 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.6773. Min Act: -0.1700
Data Index: 1544957 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.6148. Min Act: -0.1700
Data Index: 6360268 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.5523. Min Act: -0.1700
Data Index: 1107626 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4898. Min Range: -9.4898
Max Act: 8.5523. Min Act: -0.1700
Data Index: 5020327 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19