Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4480 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1456. Min Range: -5.1456
Max Act: 5.1456. Min Act: -0.1700
Data Index: 344251 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1456. Min Range: -5.1456
Max Act: 5.0206. Min Act: -0.1700
Data Index: 1068627 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1456. Min Range: -5.1456
Max Act: 5.0206. Min Act: -0.1700
Data Index: 747969 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.9894. Min Act: -0.1700
Data Index: 4484737 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.9894. Min Act: -0.1700
Data Index: 1317097 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.9581. Min Act: -0.1700
Data Index: 6705844 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8956. Min Act: -0.1700
Data Index: 3552385 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8644. Min Act: -0.1700
Data Index: 642430 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8644. Min Act: -0.1700
Data Index: 6432659 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8644. Min Act: -0.1700
Data Index: 493030 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8644. Min Act: -0.1700
Data Index: 419951 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8331. Min Act: -0.1700
Data Index: 3942596 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8331. Min Act: -0.1700
Data Index: 4196957 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8331. Min Act: -0.1700
Data Index: 3429944 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8019. Min Act: -0.1700
Data Index: 3259210 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7394. Min Act: -0.1700
Data Index: 3300536 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7394. Min Act: -0.1700
Data Index: 3175513 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7394. Min Act: -0.1700
Data Index: 3989760 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7394. Min Act: -0.1700
Data Index: 3187645 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7394. Min Act: -0.1700
Data Index: 1381028 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19