Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5793 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.4250. Min Act: -0.1700
Data Index: 6971556 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.3625. Min Act: -0.1700
Data Index: 256628 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.3312. Min Act: -0.1700
Data Index: 7584762 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.3000. Min Act: -0.1700
Data Index: 4300759 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.2687. Min Act: -0.1700
Data Index: 5460955 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.2687. Min Act: -0.1700
Data Index: 1325515 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.2687. Min Act: -0.1700
Data Index: 7168312 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.2375. Min Act: -0.1700
Data Index: 6933781 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.2375. Min Act: -0.1700
Data Index: 8365162 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.2375. Min Act: -0.1700
Data Index: 4030049 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.2062. Min Act: -0.1700
Data Index: 8141206 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.1750. Min Act: -0.1700
Data Index: 8733958 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.1750. Min Act: -0.1700
Data Index: 6608592 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.1750. Min Act: -0.1700
Data Index: 1736977 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.1437. Min Act: -0.1700
Data Index: 2306307 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.1437. Min Act: -0.1700
Data Index: 8220269 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.1125. Min Act: -0.1700
Data Index: 6017823 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.1125. Min Act: -0.1700
Data Index: 1679501 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.1437. Min Act: -0.1700
Data Index: 8387826 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4250. Min Range: -5.4250
Max Act: 5.0812. Min Act: -0.1700
Data Index: 1795040 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19