Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3867 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0707. Min Range: -4.0707
Max Act: 4.0707. Min Act: -0.1700
Data Index: 7851085 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0707. Min Range: -4.0707
Max Act: 4.0394. Min Act: -0.1700
Data Index: 1515365 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.8519. Min Act: -0.1700
Data Index: 5365243 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.7893. Min Act: -0.1700
Data Index: 5892330 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.8206. Min Act: -0.1700
Data Index: 2653061 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.7893. Min Act: -0.1700
Data Index: 8187434 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.7893. Min Act: -0.1700
Data Index: 1454318 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.7580. Min Act: -0.1700
Data Index: 4994580 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.7580. Min Act: -0.1700
Data Index: 6535825 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.7580. Min Act: -0.1700
Data Index: 6831264 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.6955. Min Act: -0.1700
Data Index: 392350 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.6485. Min Act: -0.1700
Data Index: 8072531 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.6955. Min Act: -0.1700
Data Index: 5339611 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.6955. Min Act: -0.1700
Data Index: 3028561 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.6955. Min Act: -0.1700
Data Index: 871819 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.7268. Min Act: -0.1700
Data Index: 7328429 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.6955. Min Act: -0.1700
Data Index: 7162740 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.6642. Min Act: -0.1700
Data Index: 10087 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.6955. Min Act: -0.1700
Data Index: 5733687 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0707. Min Range: -4.0707
Max Act: 3.6955. Min Act: -0.1700
Data Index: 3129612 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19