Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2878 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.9548. Min Act: -0.1700
Data Index: 7836450 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.9390. Min Act: -0.1700
Data Index: 1127694 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.9231. Min Act: -0.1700
Data Index: 5198039 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8914. Min Act: -0.1700
Data Index: 6373144 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.9073. Min Act: -0.1700
Data Index: 63149 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8756. Min Act: -0.1700
Data Index: 5108599 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8756. Min Act: -0.1700
Data Index: 6770210 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8756. Min Act: -0.1700
Data Index: 1818548 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8438. Min Act: -0.1700
Data Index: 2392466 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8597. Min Act: -0.1700
Data Index: 8493195 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8279. Min Act: -0.1700
Data Index: 1221876 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8756. Min Act: -0.1700
Data Index: 857720 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8438. Min Act: -0.1700
Data Index: 251782 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8279. Min Act: -0.1700
Data Index: 6582097 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8279. Min Act: -0.1700
Data Index: 3910845 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8279. Min Act: -0.1700
Data Index: 365106 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.8279. Min Act: -0.1700
Data Index: 7385144 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.7961. Min Act: -0.1700
Data Index: 474152 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.7961. Min Act: -0.1700
Data Index: 2020169 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9548. Min Range: -2.9548
Max Act: 2.7642. Min Act: -0.1700
Data Index: 8001525 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #19