Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1575 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1435. Min Range: -5.1435
Max Act: 5.1435. Min Act: -0.1700
Data Index: 8518996 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1435. Min Range: -5.1435
Max Act: 5.0810. Min Act: -0.1700
Data Index: 7749206 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1435. Min Range: -5.1435
Max Act: 5.0498. Min Act: -0.1700
Data Index: 8043555 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1435. Min Range: -5.1435
Max Act: 5.0498. Min Act: -0.1700
Data Index: 4265566 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1435. Min Range: -5.1435
Max Act: 5.0185. Min Act: -0.1700
Data Index: 3353980 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1435. Min Range: -5.1435
Max Act: 5.0185. Min Act: -0.1700
Data Index: 2979129 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1435. Min Range: -5.1435
Max Act: 5.0185. Min Act: -0.1700
Data Index: 489347 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1435. Min Range: -5.1435
Max Act: 5.0185. Min Act: -0.1700
Data Index: 4539275 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1435. Min Range: -5.1435
Max Act: 5.0185. Min Act: -0.1700
Data Index: 4471250 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9873. Min Act: -0.1700
Data Index: 2185235 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9873. Min Act: -0.1700
Data Index: 4077169 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9873. Min Act: -0.1700
Data Index: 235268 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9560. Min Act: -0.1700
Data Index: 8543175 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9560. Min Act: -0.1700
Data Index: 49614 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9560. Min Act: -0.1700
Data Index: 505944 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9560. Min Act: -0.1700
Data Index: 3636625 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9248. Min Act: -0.1700
Data Index: 8444997 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9248. Min Act: -0.1700
Data Index: 4696717 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9248. Min Act: -0.1700
Data Index: 6808830 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1435. Min Range: -5.1435
Max Act: 4.9560. Min Act: -0.1700
Data Index: 2392950 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19