Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3657 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8982. Min Range: -8.8982
Max Act: 8.8982. Min Act: -0.1700
Data Index: 1289909 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8982. Min Range: -8.8982
Max Act: 8.6482. Min Act: -0.1700
Data Index: 4660963 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.9607. Min Act: -0.1700
Data Index: 8423820 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.6169. Min Act: -0.1700
Data Index: 268275 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.5232. Min Act: -0.1700
Data Index: 859481 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.4607. Min Act: -0.1700
Data Index: 1850535 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.3982. Min Act: -0.1700
Data Index: 5331193 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.3982. Min Act: -0.1700
Data Index: 3862480 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.3982. Min Act: -0.1700
Data Index: 5008023 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.3982. Min Act: -0.1700
Data Index: 1514025 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.4294. Min Act: -0.1700
Data Index: 38596 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.3357. Min Act: -0.1700
Data Index: 7718472 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.2419. Min Act: -0.1700
Data Index: 6881474 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.2419. Min Act: -0.1700
Data Index: 7908359 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.2107. Min Act: -0.1700
Data Index: 3266689 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.2107. Min Act: -0.1700
Data Index: 6331865 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.1482. Min Act: -0.1700
Data Index: 1370946 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.1482. Min Act: -0.1700
Data Index: 7086242 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.1482. Min Act: -0.1700
Data Index: 6677181 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8982. Min Range: -8.8982
Max Act: 7.1169. Min Act: -0.1700
Data Index: 222774 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19