Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4075 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.9865. Min Act: -0.1700
Data Index: 4981985 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.9240. Min Act: -0.1700
Data Index: 8204175 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.8928. Min Act: -0.1700
Data Index: 6328924 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.8928. Min Act: -0.1700
Data Index: 4272308 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.8928. Min Act: -0.1700
Data Index: 7214757 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.8615. Min Act: -0.1700
Data Index: 8761793 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.8303. Min Act: -0.1700
Data Index: 6979636 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.7990. Min Act: -0.1700
Data Index: 4982000 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.7678. Min Act: -0.1700
Data Index: 7873579 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.7053. Min Act: -0.1700
Data Index: 1254473 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.6740. Min Act: -0.1700
Data Index: 2235252 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.6428. Min Act: -0.1700
Data Index: 4768278 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.6115. Min Act: -0.1700
Data Index: 6328925 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.5803. Min Act: -0.1700
Data Index: 4869428 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.5490. Min Act: -0.1700
Data Index: 5764920 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.4865. Min Act: -0.1700
Data Index: 4637449 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.4865. Min Act: -0.1700
Data Index: 7220999 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.4865. Min Act: -0.1700
Data Index: 2478424 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.4553. Min Act: -0.1700
Data Index: 2739977 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9865. Min Range: -6.9865
Max Act: 6.4553. Min Act: -0.1700
Data Index: 598562 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19