Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1416 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.6751. Min Act: -0.1700
Data Index: 1860676 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.5704. Min Act: -0.1700
Data Index: 2358777 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.5442. Min Act: -0.1700
Data Index: 4199445 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.5267. Min Act: -0.1700
Data Index: 1561324 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.5267. Min Act: -0.1700
Data Index: 6859260 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4916. Min Act: -0.1700
Data Index: 5375774 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4916. Min Act: -0.1700
Data Index: 3871176 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4916. Min Act: -0.1700
Data Index: 8400208 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4916. Min Act: -0.1700
Data Index: 8408523 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4740. Min Act: -0.1700
Data Index: 6307084 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4564. Min Act: -0.1700
Data Index: 8615974 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4652. Min Act: -0.1700
Data Index: 382844 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4564. Min Act: -0.1700
Data Index: 5899626 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4476. Min Act: -0.1700
Data Index: 276972 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4476. Min Act: -0.1700
Data Index: 4069703 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4300. Min Act: -0.1700
Data Index: 5690320 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4212. Min Act: -0.1700
Data Index: 4207561 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4388. Min Act: -0.1700
Data Index: 1405598 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4124. Min Act: -0.1700
Data Index: 4739888 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6751. Min Range: -1.6751
Max Act: 1.4212. Min Act: -0.1700
Data Index: 4778143 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19