Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2463 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3265. Min Range: -7.3265
Max Act: 7.3265. Min Act: -0.1700
Data Index: 3781138 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.6703. Min Act: -0.1700
Data Index: 593643 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.6703. Min Act: -0.1700
Data Index: 2050607 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.6078. Min Act: -0.1700
Data Index: 4460037 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.5453. Min Act: -0.1700
Data Index: 2654933 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.5140. Min Act: -0.1700
Data Index: 1438919 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.5140. Min Act: -0.1700
Data Index: 1458046 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.4828. Min Act: -0.1700
Data Index: 3570890 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.4203. Min Act: -0.1700
Data Index: 1583672 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.4203. Min Act: -0.1700
Data Index: 4010315 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.4203. Min Act: -0.1700
Data Index: 4262831 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.3578. Min Act: -0.1700
Data Index: 5224147 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.3578. Min Act: -0.1700
Data Index: 8540378 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.3578. Min Act: -0.1700
Data Index: 2475952 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.3265. Min Act: -0.1700
Data Index: 4041584 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.3578. Min Act: -0.1700
Data Index: 2262336 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.3265. Min Act: -0.1700
Data Index: 23786 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.3265. Min Act: -0.1700
Data Index: 8511231 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.2953. Min Act: -0.1700
Data Index: 4592452 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3265. Min Range: -7.3265
Max Act: 6.2953. Min Act: -0.1700
Data Index: 1395896 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #19