Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5786 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1375. Min Range: -8.1375
Max Act: 8.1375. Min Act: -0.1700
Data Index: 7884796 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1375. Min Range: -8.1375
Max Act: 7.8875. Min Act: -0.1700
Data Index: 454929 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1375. Min Range: -8.1375
Max Act: 7.4812. Min Act: -0.1700
Data Index: 1754538 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1375. Min Range: -8.1375
Max Act: 7.4187. Min Act: -0.1700
Data Index: 530375 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1375. Min Range: -8.1375
Max Act: 7.3250. Min Act: -0.1700
Data Index: 8616608 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1375. Min Range: -8.1375
Max Act: 7.2312. Min Act: -0.1700
Data Index: 5073149 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1375. Min Range: -8.1375
Max Act: 7.1375. Min Act: -0.1700
Data Index: 3861561 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1375. Min Range: -8.1375
Max Act: 7.1375. Min Act: -0.1700
Data Index: 1712750 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.9812. Min Act: -0.1700
Data Index: 6146572 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.9812. Min Act: -0.1700
Data Index: 1754537 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.9500. Min Act: -0.1700
Data Index: 194583 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.8875. Min Act: -0.1700
Data Index: 806313 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.8562. Min Act: -0.1700
Data Index: 7357260 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.8250. Min Act: -0.1700
Data Index: 5489730 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.8250. Min Act: -0.1700
Data Index: 252513 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.8250. Min Act: -0.1700
Data Index: 8508581 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.7625. Min Act: -0.1700
Data Index: 1353996 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.7937. Min Act: -0.1700
Data Index: 8228333 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.7937. Min Act: -0.1700
Data Index: 2694880 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1375. Min Range: -8.1375
Max Act: 6.7937. Min Act: -0.1700
Data Index: 6417216 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19