Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3044 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.4165. Min Range: -11.4165
Max Act: 11.4165. Min Act: -0.1700
Data Index: 967605 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.4165. Min Range: -11.4165
Max Act: 11.1665. Min Act: -0.1700
Data Index: 3989053 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.4165. Min Range: -11.4165
Max Act: 11.1040. Min Act: -0.1700
Data Index: 6559110 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.4165. Min Range: -11.4165
Max Act: 11.0415. Min Act: -0.1700
Data Index: 1235056 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.9165. Min Act: -0.1700
Data Index: 345519 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.9165. Min Act: -0.1700
Data Index: 6015953 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.8540. Min Act: -0.1700
Data Index: 4404341 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.9165. Min Act: -0.1700
Data Index: 523821 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.7915. Min Act: -0.1700
Data Index: 2723341 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.7290. Min Act: -0.1700
Data Index: 2057294 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.6665. Min Act: -0.1700
Data Index: 6983371 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.4790. Min Act: -0.1700
Data Index: 857185 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.4790. Min Act: -0.1700
Data Index: 2589427 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.4790. Min Act: -0.1700
Data Index: 4087557 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.4790. Min Act: -0.1700
Data Index: 7221352 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.4790. Min Act: -0.1700
Data Index: 5927152 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.4165. Min Act: -0.1700
Data Index: 6386872 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.3540. Min Act: -0.1700
Data Index: 7292543 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.4165. Min Act: -0.1700
Data Index: 2005392 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.4165. Min Range: -11.4165
Max Act: 10.4165. Min Act: -0.1700
Data Index: 857186 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #19