Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5700 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0851. Min Range: -6.0851
Max Act: 6.0851. Min Act: -0.1700
Data Index: 923968 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0851. Min Range: -6.0851
Max Act: 6.0226. Min Act: -0.1700
Data Index: 6847706 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.9913. Min Act: -0.1700
Data Index: 376193 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.9913. Min Act: -0.1700
Data Index: 2985215 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.9601. Min Act: -0.1700
Data Index: 5271204 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8663. Min Act: -0.1700
Data Index: 4393250 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8976. Min Act: -0.1700
Data Index: 5589824 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8663. Min Act: -0.1700
Data Index: 111641 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8663. Min Act: -0.1700
Data Index: 1851918 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8351. Min Act: -0.1700
Data Index: 8741187 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8351. Min Act: -0.1700
Data Index: 1216710 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8351. Min Act: -0.1700
Data Index: 7070234 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8351. Min Act: -0.1700
Data Index: 5940207 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8038. Min Act: -0.1700
Data Index: 6344911 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8038. Min Act: -0.1700
Data Index: 3349696 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8038. Min Act: -0.1700
Data Index: 5491719 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8038. Min Act: -0.1700
Data Index: 7291123 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.8038. Min Act: -0.1700
Data Index: 5790228 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.7726. Min Act: -0.1700
Data Index: 7056545 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0851. Min Range: -6.0851
Max Act: 5.7726. Min Act: -0.1700
Data Index: 3199377 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19