Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4788 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7643. Min Range: -6.7643
Max Act: 6.7643. Min Act: -0.1700
Data Index: 3859891 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7643. Min Range: -6.7643
Max Act: 6.1393. Min Act: -0.1700
Data Index: 7333475 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7643. Min Range: -6.7643
Max Act: 6.1081. Min Act: -0.1700
Data Index: 3083840 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7643. Min Range: -6.7643
Max Act: 6.0768. Min Act: -0.1700
Data Index: 107904 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7643. Min Range: -6.7643
Max Act: 6.0768. Min Act: -0.1700
Data Index: 4138215 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7643. Min Range: -6.7643
Max Act: 6.0768. Min Act: -0.1700
Data Index: 2681603 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7643. Min Range: -6.7643
Max Act: 6.0456. Min Act: -0.1700
Data Index: 5538985 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.9831. Min Act: -0.1700
Data Index: 2134201 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.9831. Min Act: -0.1700
Data Index: 8115203 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.9831. Min Act: -0.1700
Data Index: 3474095 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.9831. Min Act: -0.1700
Data Index: 8661320 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.8893. Min Act: -0.1700
Data Index: 7102157 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.9206. Min Act: -0.1700
Data Index: 6986824 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.9206. Min Act: -0.1700
Data Index: 1393894 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.9206. Min Act: -0.1700
Data Index: 2387726 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.8581. Min Act: -0.1700
Data Index: 2810398 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.8581. Min Act: -0.1700
Data Index: 3509289 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.7956. Min Act: -0.1700
Data Index: 3053986 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.7956. Min Act: -0.1700
Data Index: 6781308 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7643. Min Range: -6.7643
Max Act: 5.7956. Min Act: -0.1700
Data Index: 715661 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19