Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2871 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9868. Min Act: -0.1700
Data Index: 4369968 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9556. Min Act: -0.1700
Data Index: 7788013 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9556. Min Act: -0.1699
Data Index: 4532797 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.9243. Min Act: -0.1700
Data Index: 2237097 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8931. Min Act: -0.1700
Data Index: 4895746 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8306. Min Act: -0.1700
Data Index: 1448733 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 7518540 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.8306. Min Act: -0.1700
Data Index: 4508815 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 2617191 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 8586636 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 4888405 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 1722939 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 7688522 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 2678316 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 6211234 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 7688521 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7993. Min Act: -0.1700
Data Index: 4092422 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7681. Min Act: -0.1700
Data Index: 2547934 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7681. Min Act: -0.1700
Data Index: 1342841 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9868. Min Range: -4.9868
Max Act: 4.7681. Min Act: -0.1700
Data Index: 7043763 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #19