Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 501 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2246. Min Range: -4.2246
Max Act: 4.2246. Min Act: -0.1700
Data Index: 3422310 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2246. Min Range: -4.2246
Max Act: 4.1620. Min Act: -0.1700
Data Index: 5307665 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2246. Min Range: -4.2246
Max Act: 4.1308. Min Act: -0.1700
Data Index: 3515936 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2246. Min Range: -4.2246
Max Act: 4.1308. Min Act: -0.1700
Data Index: 2587722 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2246. Min Range: -4.2246
Max Act: 4.0995. Min Act: -0.1700
Data Index: 3386436 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2246. Min Range: -4.2246
Max Act: 4.0370. Min Act: -0.1700
Data Index: 3905409 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2246. Min Range: -4.2246
Max Act: 4.0058. Min Act: -0.1700
Data Index: 1528090 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9745. Min Act: -0.1700
Data Index: 2500258 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9745. Min Act: -0.1700
Data Index: 2468889 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9745. Min Act: -0.1700
Data Index: 1804374 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9432. Min Act: -0.1700
Data Index: 1808914 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9745. Min Act: -0.1700
Data Index: 7544759 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9432. Min Act: -0.1700
Data Index: 2248110 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9432. Min Act: -0.1700
Data Index: 4305033 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9120. Min Act: -0.1700
Data Index: 7756754 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9120. Min Act: -0.1700
Data Index: 2840078 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9120. Min Act: -0.1700
Data Index: 3340538 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9120. Min Act: -0.1700
Data Index: 4399185 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.9120. Min Act: -0.1700
Data Index: 8507058 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2246. Min Range: -4.2246
Max Act: 3.8807. Min Act: -0.1700
Data Index: 1496407 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19