Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3130 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0471. Min Range: -7.0471
Max Act: 7.0471. Min Act: -0.1700
Data Index: 7723290 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0471. Min Range: -7.0471
Max Act: 6.5471. Min Act: -0.1700
Data Index: 608752 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0471. Min Range: -7.0471
Max Act: 6.2658. Min Act: -0.1700
Data Index: 8596877 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0471. Min Range: -7.0471
Max Act: 6.2033. Min Act: -0.1700
Data Index: 8736039 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0471. Min Range: -7.0471
Max Act: 6.1721. Min Act: -0.1700
Data Index: 5115352 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0471. Min Range: -7.0471
Max Act: 6.1721. Min Act: -0.1700
Data Index: 1623509 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0471. Min Range: -7.0471
Max Act: 6.1096. Min Act: -0.1700
Data Index: 1180692 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0471. Min Range: -7.0471
Max Act: 6.0783. Min Act: -0.1700
Data Index: 2842545 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.9846. Min Act: -0.1700
Data Index: 2965243 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0471. Min Range: -7.0471
Max Act: 6.0158. Min Act: -0.1700
Data Index: 3529283 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.9846. Min Act: -0.1700
Data Index: 6018949 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.9846. Min Act: -0.1700
Data Index: 1289385 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.9221. Min Act: -0.1700
Data Index: 5650184 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.9533. Min Act: -0.1700
Data Index: 6293491 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.9221. Min Act: -0.1700
Data Index: 683856 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.8596. Min Act: -0.1700
Data Index: 4797309 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.8596. Min Act: -0.1700
Data Index: 4986339 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.8596. Min Act: -0.1700
Data Index: 6738116 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.8283. Min Act: -0.1700
Data Index: 443351 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0471. Min Range: -7.0471
Max Act: 5.8596. Min Act: -0.1700
Data Index: 3080625 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19