Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2606 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.4910. Min Act: -0.1700
Data Index: 1100011 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.3035. Min Act: -0.1700
Data Index: 6294211 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.2410. Min Act: -0.1700
Data Index: 3058187 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.2097. Min Act: -0.1700
Data Index: 5602487 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.1472. Min Act: -0.1700
Data Index: 103540 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.0847. Min Act: -0.1700
Data Index: 6805121 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.0535. Min Act: -0.1700
Data Index: 8457731 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.0847. Min Act: -0.1700
Data Index: 2704330 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.0847. Min Act: -0.1700
Data Index: 2601992 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.0222. Min Act: -0.1700
Data Index: 8408762 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.0535. Min Act: -0.1700
Data Index: 2231461 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.0222. Min Act: -0.1700
Data Index: 31808 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4910. Min Range: -5.4910
Max Act: 5.0222. Min Act: -0.1700
Data Index: 2861839 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4910. Min Range: -5.4910
Max Act: 4.9597. Min Act: -0.1700
Data Index: 2735327 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4910. Min Range: -5.4910
Max Act: 4.9910. Min Act: -0.1700
Data Index: 3968414 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4910. Min Range: -5.4910
Max Act: 4.9910. Min Act: -0.1700
Data Index: 3146541 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4910. Min Range: -5.4910
Max Act: 4.9597. Min Act: -0.1700
Data Index: 2495984 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4910. Min Range: -5.4910
Max Act: 4.9285. Min Act: -0.1700
Data Index: 2982830 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4910. Min Range: -5.4910
Max Act: 4.8972. Min Act: -0.1700
Data Index: 8417983 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4910. Min Range: -5.4910
Max Act: 4.8972. Min Act: -0.1700
Data Index: 8516848 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19