Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3417 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.4909. Min Act: -0.1700
Data Index: 44274 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.3659. Min Act: -0.1700
Data Index: 5896716 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.2721. Min Act: -0.1700
Data Index: 369458 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.2409. Min Act: -0.1700
Data Index: 44275 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.2409. Min Act: -0.1700
Data Index: 6359374 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.2409. Min Act: -0.1700
Data Index: 783958 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.1471. Min Act: -0.1700
Data Index: 3173303 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.1471. Min Act: -0.1700
Data Index: 6359375 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.1471. Min Act: -0.1700
Data Index: 6359380 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.1159. Min Act: -0.1700
Data Index: 44267 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.0846. Min Act: -0.1700
Data Index: 6359381 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.0846. Min Act: -0.1700
Data Index: 175879 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.0534. Min Act: -0.1700
Data Index: 4232170 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.0221. Min Act: -0.1700
Data Index: 44269 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4909. Min Range: -5.4909
Max Act: 5.0221. Min Act: -0.1700
Data Index: 44261 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4909. Min Range: -5.4909
Max Act: 4.9596. Min Act: -0.1700
Data Index: 44276 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4909. Min Range: -5.4909
Max Act: 4.9284. Min Act: -0.1700
Data Index: 6621403 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4909. Min Range: -5.4909
Max Act: 4.9284. Min Act: -0.1700
Data Index: 6359382 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4909. Min Range: -5.4909
Max Act: 4.9284. Min Act: -0.1699
Data Index: 10618 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4909. Min Range: -5.4909
Max Act: 4.8971. Min Act: -0.1700
Data Index: 5346451 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19