Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2635 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.7038. Min Act: -0.1700
Data Index: 794190 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.6413. Min Act: -0.1700
Data Index: 7593553 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.6101. Min Act: -0.1700
Data Index: 8297355 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.6101. Min Act: -0.1700
Data Index: 3011154 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.6101. Min Act: -0.1700
Data Index: 384341 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.5788. Min Act: -0.1700
Data Index: 6047747 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.5476. Min Act: -0.1700
Data Index: 7148828 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.5788. Min Act: -0.1700
Data Index: 407865 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.5163. Min Act: -0.1700
Data Index: 2273290 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4851. Min Act: -0.1700
Data Index: 2273295 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4851. Min Act: -0.1700
Data Index: 8384530 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4851. Min Act: -0.1700
Data Index: 4910911 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4851. Min Act: -0.1700
Data Index: 2819230 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4538. Min Act: -0.1700
Data Index: 2336129 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4851. Min Act: -0.1700
Data Index: 948243 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4851. Min Act: -0.1700
Data Index: 6076363 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4538. Min Act: -0.1700
Data Index: 2811857 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4538. Min Act: -0.1700
Data Index: 2659715 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4851. Min Act: -0.1700
Data Index: 2551466 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7038. Min Range: -5.7038
Max Act: 5.4538. Min Act: -0.1700
Data Index: 6501803 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19