Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4188 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.2205. Min Act: -0.1700
Data Index: 8138260 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.1677. Min Act: -0.1699
Data Index: 1077130 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.1501. Min Act: -0.1700
Data Index: 6987948 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.1326. Min Act: -0.1700
Data Index: 6987941 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.1326. Min Act: -0.1700
Data Index: 2366013 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.1150. Min Act: -0.1699
Data Index: 5996910 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.1150. Min Act: -0.1700
Data Index: 4058124 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.1150. Min Act: -0.1700
Data Index: 5414810 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0800. Min Act: -0.1700
Data Index: 5414811 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0975. Min Act: -0.1700
Data Index: 2710672 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0975. Min Act: -0.1700
Data Index: 3552737 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0975. Min Act: -0.1699
Data Index: 8335884 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0800. Min Act: -0.1699
Data Index: 3819743 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0975. Min Act: -0.1700
Data Index: 713708 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0975. Min Act: -0.1700
Data Index: 7556732 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0800. Min Act: -0.1700
Data Index: 2366012 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0975. Min Act: -0.1700
Data Index: 6713593 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0975. Min Act: -0.1694
Data Index: 5276579 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0625. Min Act: -0.1700
Data Index: 1042991 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2205. Min Range: -1.2205
Max Act: 1.0800. Min Act: -0.1700
Data Index: 3847436 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19