Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2009 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.7788. Min Act: -0.1700
Data Index: 6709609 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.7475. Min Act: -0.1700
Data Index: 7393656 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.7788. Min Act: -0.1700
Data Index: 8153151 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.7163. Min Act: -0.1700
Data Index: 7004138 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.7163. Min Act: -0.1700
Data Index: 5055362 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6850. Min Act: -0.1700
Data Index: 8802856 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.7163. Min Act: -0.1700
Data Index: 7004135 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6850. Min Act: -0.1700
Data Index: 3640400 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6538. Min Act: -0.1700
Data Index: 1005343 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6850. Min Act: -0.1699
Data Index: 5725571 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6850. Min Act: -0.1700
Data Index: 2820775 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6225. Min Act: -0.1700
Data Index: 8244828 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6538. Min Act: -0.1700
Data Index: 4146689 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6538. Min Act: -0.1699
Data Index: 6516737 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6538. Min Act: -0.1700
Data Index: 4119823 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6225. Min Act: -0.1700
Data Index: 6327008 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6538. Min Act: -0.1700
Data Index: 7459678 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6538. Min Act: -0.1700
Data Index: 7415812 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6850. Min Act: -0.1700
Data Index: 5010428 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7788. Min Range: -5.7788
Max Act: 5.6538. Min Act: -0.1700
Data Index: 2393606 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19