Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2218 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3024. Min Range: -5.3024
Max Act: 5.3024. Min Act: -0.1700
Data Index: 7348756 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3024. Min Range: -5.3024
Max Act: 5.1462. Min Act: -0.1700
Data Index: 6552788 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3024. Min Range: -5.3024
Max Act: 5.0837. Min Act: -0.1700
Data Index: 3280394 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3024. Min Range: -5.3024
Max Act: 5.0212. Min Act: -0.1700
Data Index: 5528237 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3024. Min Range: -5.3024
Max Act: 5.0212. Min Act: -0.1700
Data Index: 1214525 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.9587. Min Act: -0.1700
Data Index: 6355580 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.9587. Min Act: -0.1700
Data Index: 1871349 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8962. Min Act: -0.1700
Data Index: 4337206 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8962. Min Act: -0.1700
Data Index: 4959701 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8962. Min Act: -0.1700
Data Index: 378461 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8337. Min Act: -0.1700
Data Index: 1993555 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8649. Min Act: -0.1700
Data Index: 1153907 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8649. Min Act: -0.1700
Data Index: 378442 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8337. Min Act: -0.1700
Data Index: 320234 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8337. Min Act: -0.1700
Data Index: 378448 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8024. Min Act: -0.1700
Data Index: 8069550 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8024. Min Act: -0.1700
Data Index: 8822017 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.8337. Min Act: -0.1700
Data Index: 6998374 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.7712. Min Act: -0.1700
Data Index: 354331 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3024. Min Range: -5.3024
Max Act: 4.7712. Min Act: -0.1700
Data Index: 378451 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19