Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4063 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.4328. Min Act: -0.1700
Data Index: 4616523 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.3078. Min Act: -0.1700
Data Index: 4485747 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.3078. Min Act: -0.1700
Data Index: 784245 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.2765. Min Act: -0.1700
Data Index: 4444527 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.2140. Min Act: -0.1700
Data Index: 5640675 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.2140. Min Act: -0.1700
Data Index: 4389468 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1515. Min Act: -0.1700
Data Index: 7626478 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1828. Min Act: -0.1700
Data Index: 7990202 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1515. Min Act: -0.1700
Data Index: 8394863 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1515. Min Act: -0.1700
Data Index: 6214527 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1202. Min Act: -0.1700
Data Index: 6388964 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1202. Min Act: -0.1700
Data Index: 2302308 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1202. Min Act: -0.1700
Data Index: 7461768 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1202. Min Act: -0.1700
Data Index: 3789000 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0890. Min Act: -0.1700
Data Index: 4661274 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0890. Min Act: -0.1700
Data Index: 7017318 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0890. Min Act: -0.1700
Data Index: 4874738 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0890. Min Act: -0.1700
Data Index: 516335 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.1202. Min Act: -0.1700
Data Index: 690544 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4328. Min Range: -4.4328
Max Act: 4.0890. Min Act: -0.1700
Data Index: 2406865 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #19