Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2453 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5273. Min Range: -5.5273
Max Act: 5.5273. Min Act: -0.1700
Data Index: 3603513 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5273. Min Range: -5.5273
Max Act: 5.3711. Min Act: -0.1700
Data Index: 1262580 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5273. Min Range: -5.5273
Max Act: 5.1836. Min Act: -0.1700
Data Index: 3620487 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5273. Min Range: -5.5273
Max Act: 5.1836. Min Act: -0.1700
Data Index: 2484942 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5273. Min Range: -5.5273
Max Act: 5.1211. Min Act: -0.1700
Data Index: 2642109 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5273. Min Range: -5.5273
Max Act: 5.0898. Min Act: -0.1700
Data Index: 4759857 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5273. Min Range: -5.5273
Max Act: 5.0273. Min Act: -0.1700
Data Index: 1350624 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5273. Min Range: -5.5273
Max Act: 5.0273. Min Act: -0.1700
Data Index: 703241 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5273. Min Range: -5.5273
Max Act: 5.0586. Min Act: -0.1700
Data Index: 5497023 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5273. Min Range: -5.5273
Max Act: 5.0273. Min Act: -0.1700
Data Index: 4443016 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5273. Min Range: -5.5273
Max Act: 4.9961. Min Act: -0.1700
Data Index: 6293569 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5273. Min Range: -5.5273
Max Act: 4.9961. Min Act: -0.1700
Data Index: 2135940 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5273. Min Range: -5.5273
Max Act: 4.9961. Min Act: -0.1700
Data Index: 4200822 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5273. Min Range: -5.5273
Max Act: 4.9648. Min Act: -0.1700
Data Index: 4721898 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5273. Min Range: -5.5273
Max Act: 4.9648. Min Act: -0.1700
Data Index: 5943367 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5273. Min Range: -5.5273
Max Act: 4.9336. Min Act: -0.1700
Data Index: 4090379 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5273. Min Range: -5.5273
Max Act: 4.9336. Min Act: -0.1700
Data Index: 7306163 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5273. Min Range: -5.5273
Max Act: 4.9336. Min Act: -0.1700
Data Index: 1262579 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5273. Min Range: -5.5273
Max Act: 4.9336. Min Act: -0.1700
Data Index: 789008 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5273. Min Range: -5.5273
Max Act: 4.9023. Min Act: -0.1700
Data Index: 3724960 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19