Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4547 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.9302. Min Act: -0.1700
Data Index: 700843 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.8677. Min Act: -0.1700
Data Index: 8001482 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.8677. Min Act: -0.1700
Data Index: 5974782 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.8677. Min Act: -0.1700
Data Index: 603852 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.7740. Min Act: -0.1700
Data Index: 2296278 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.6802. Min Act: -0.1700
Data Index: 1611320 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.6490. Min Act: -0.1700
Data Index: 328492 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.5240. Min Act: -0.1700
Data Index: 4201178 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.4927. Min Act: -0.1700
Data Index: 3749839 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.4927. Min Act: -0.1700
Data Index: 6896001 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.4615. Min Act: -0.1700
Data Index: 1331831 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.4302. Min Act: -0.1700
Data Index: 889418 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.4302. Min Act: -0.1700
Data Index: 6994203 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.4302. Min Act: -0.1700
Data Index: 3917271 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.4302. Min Act: -0.1700
Data Index: 690866 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.3990. Min Act: -0.1700
Data Index: 6939263 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.3990. Min Act: -0.1700
Data Index: 73853 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.3990. Min Act: -0.1700
Data Index: 717262 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.4302. Min Act: -0.1700
Data Index: 5301560 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9302. Min Range: -6.9302
Max Act: 6.3990. Min Act: -0.1700
Data Index: 7849395 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19