Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2361 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3908. Min Range: -5.3908
Max Act: 5.3908. Min Act: -0.1700
Data Index: 4687973 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3908. Min Range: -5.3908
Max Act: 5.3283. Min Act: -0.1700
Data Index: 3547257 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3908. Min Range: -5.3908
Max Act: 5.2346. Min Act: -0.1700
Data Index: 7425155 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3908. Min Range: -5.3908
Max Act: 5.1408. Min Act: -0.1700
Data Index: 8686543 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3908. Min Range: -5.3908
Max Act: 5.1096. Min Act: -0.1700
Data Index: 7542414 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3908. Min Range: -5.3908
Max Act: 5.0783. Min Act: -0.1700
Data Index: 4519601 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3908. Min Range: -5.3908
Max Act: 5.0471. Min Act: -0.1700
Data Index: 4852465 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3908. Min Range: -5.3908
Max Act: 5.0158. Min Act: -0.1700
Data Index: 8814971 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3908. Min Range: -5.3908
Max Act: 5.0471. Min Act: -0.1700
Data Index: 7651235 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3908. Min Range: -5.3908
Max Act: 5.0158. Min Act: -0.1700
Data Index: 1020988 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3908. Min Range: -5.3908
Max Act: 4.9846. Min Act: -0.1700
Data Index: 2591475 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3908. Min Range: -5.3908
Max Act: 4.9533. Min Act: -0.1700
Data Index: 4362967 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3908. Min Range: -5.3908
Max Act: 4.9533. Min Act: -0.1700
Data Index: 4013163 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3908. Min Range: -5.3908
Max Act: 4.9846. Min Act: -0.1700
Data Index: 7542395 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3908. Min Range: -5.3908
Max Act: 4.9533. Min Act: -0.1700
Data Index: 7417417 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3908. Min Range: -5.3908
Max Act: 4.9533. Min Act: -0.1700
Data Index: 851954 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3908. Min Range: -5.3908
Max Act: 4.9221. Min Act: -0.1700
Data Index: 8320908 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3908. Min Range: -5.3908
Max Act: 4.9221. Min Act: -0.1700
Data Index: 8315607 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3908. Min Range: -5.3908
Max Act: 4.9221. Min Act: -0.1700
Data Index: 4409347 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3908. Min Range: -5.3908
Max Act: 4.9221. Min Act: -0.1700
Data Index: 1292301 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19