Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1651 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.4248. Min Act: -0.1700
Data Index: 1635716 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.3936. Min Act: -0.1700
Data Index: 2093177 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.3623. Min Act: -0.1700
Data Index: 8313034 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.3310. Min Act: -0.1700
Data Index: 7247276 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.3310. Min Act: -0.1700
Data Index: 8147001 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2998. Min Act: -0.1700
Data Index: 1288327 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2998. Min Act: -0.1700
Data Index: 5062635 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2998. Min Act: -0.1700
Data Index: 715520 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2998. Min Act: -0.1700
Data Index: 8215407 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2685. Min Act: -0.1700
Data Index: 6181326 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2685. Min Act: -0.1700
Data Index: 3140716 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2685. Min Act: -0.1700
Data Index: 4065884 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2685. Min Act: -0.1700
Data Index: 1217511 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2373. Min Act: -0.1700
Data Index: 7887760 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2685. Min Act: -0.1700
Data Index: 7759398 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2685. Min Act: -0.1700
Data Index: 5837157 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2685. Min Act: -0.1700
Data Index: 3917170 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2685. Min Act: -0.1700
Data Index: 5892958 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2373. Min Act: -0.1700
Data Index: 7666969 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4248. Min Range: -4.4248
Max Act: 4.2373. Min Act: -0.1700
Data Index: 1497764 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19