Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5278 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.8424. Min Act: -0.1700
Data Index: 412177 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.9049. Min Act: -0.1700
Data Index: 8774748 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.7799. Min Act: -0.1700
Data Index: 1644748 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.6549. Min Act: -0.1700
Data Index: 5800000 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.6549. Min Act: -0.1700
Data Index: 8767063 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.5299. Min Act: -0.1700
Data Index: 1097352 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.4049. Min Act: -0.1700
Data Index: 1956154 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.2799. Min Act: -0.1700
Data Index: 3704208 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.3424. Min Act: -0.1700
Data Index: 7120158 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.3424. Min Act: -0.1700
Data Index: 1364234 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.2799. Min Act: -0.1700
Data Index: 81156 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.2174. Min Act: -0.1700
Data Index: 1754832 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.2174. Min Act: -0.1700
Data Index: 624456 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.1549. Min Act: -0.1700
Data Index: 2220985 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.2174. Min Act: -0.1700
Data Index: 811656 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.1549. Min Act: -0.1700
Data Index: 2007283 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.1549. Min Act: -0.1700
Data Index: 4147456 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.1549. Min Act: -0.1700
Data Index: 3702837 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.0299. Min Act: -0.1700
Data Index: 7941374 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.9049. Min Range: -13.9049
Max Act: 13.0299. Min Act: -0.1700
Data Index: 4675015 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19