Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1585 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2270. Min Range: -5.2270
Max Act: 5.2270. Min Act: -0.1700
Data Index: 807668 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2270. Min Range: -5.2270
Max Act: 5.1957. Min Act: -0.1700
Data Index: 922872 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2270. Min Range: -5.2270
Max Act: 5.1020. Min Act: -0.1700
Data Index: 6651703 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2270. Min Range: -5.2270
Max Act: 5.0707. Min Act: -0.1700
Data Index: 46151 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2270. Min Range: -5.2270
Max Act: 5.0395. Min Act: -0.1700
Data Index: 519291 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2270. Min Range: -5.2270
Max Act: 5.0395. Min Act: -0.1700
Data Index: 6884356 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9770. Min Act: -0.1700
Data Index: 5845977 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9770. Min Act: -0.1700
Data Index: 2029593 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9145. Min Act: -0.1700
Data Index: 5811077 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9457. Min Act: -0.1700
Data Index: 4408561 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9457. Min Act: -0.1700
Data Index: 2204708 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9145. Min Act: -0.1700
Data Index: 2091167 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9457. Min Act: -0.1700
Data Index: 3891801 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9145. Min Act: -0.1700
Data Index: 6816724 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.8832. Min Act: -0.1700
Data Index: 2582162 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9145. Min Act: -0.1700
Data Index: 6585101 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9145. Min Act: -0.1700
Data Index: 8055613 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.9145. Min Act: -0.1700
Data Index: 3117602 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.8832. Min Act: -0.1700
Data Index: 3227757 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2270. Min Range: -5.2270
Max Act: 4.8832. Min Act: -0.1700
Data Index: 2599066 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19