Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4635 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.9934. Min Act: -0.1700
Data Index: 8548989 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.9934. Min Act: -0.1700
Data Index: 3590124 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.9465. Min Act: -0.1700
Data Index: 336232 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.9465. Min Act: -0.1700
Data Index: 7735946 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.8840. Min Act: -0.1700
Data Index: 5206154 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.8683. Min Act: -0.1700
Data Index: 3027406 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.8371. Min Act: -0.1700
Data Index: 3036164 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.8214. Min Act: -0.1700
Data Index: 6515223 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.8214. Min Act: -0.1700
Data Index: 8044377 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.8058. Min Act: -0.1700
Data Index: 8508165 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.8058. Min Act: -0.1700
Data Index: 2522965 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.8058. Min Act: -0.1700
Data Index: 5441009 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.7745. Min Act: -0.1700
Data Index: 4213051 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.7902. Min Act: -0.1700
Data Index: 4771648 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.8058. Min Act: -0.1700
Data Index: 6783109 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.7902. Min Act: -0.1700
Data Index: 2161672 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.7745. Min Act: -0.1700
Data Index: 2677579 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.7902. Min Act: -0.1700
Data Index: 8334854 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.7589. Min Act: -0.1700
Data Index: 4140355 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9934. Min Range: -3.9934
Max Act: 3.7589. Min Act: -0.1700
Data Index: 3207651 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19