Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1360 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.4857. Min Act: -0.1700
Data Index: 1168218 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.4232. Min Act: -0.1700
Data Index: 3228522 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.4857. Min Act: -0.1700
Data Index: 6932301 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.4232. Min Act: -0.1700
Data Index: 5306076 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.4232. Min Act: -0.1700
Data Index: 2027715 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.4232. Min Act: -0.1700
Data Index: 1406578 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3919. Min Act: -0.1700
Data Index: 1719437 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3919. Min Act: -0.1700
Data Index: 6244096 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3607. Min Act: -0.1700
Data Index: 672727 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3607. Min Act: -0.1700
Data Index: 3472997 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3607. Min Act: -0.1700
Data Index: 1473720 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3607. Min Act: -0.1700
Data Index: 4220587 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3607. Min Act: -0.1700
Data Index: 2653926 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3294. Min Act: -0.1700
Data Index: 5664997 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3294. Min Act: -0.1700
Data Index: 4517757 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3294. Min Act: -0.1700
Data Index: 2970468 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3294. Min Act: -0.1700
Data Index: 2627684 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3294. Min Act: -0.1700
Data Index: 3531231 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3294. Min Act: -0.1700
Data Index: 4950452 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4857. Min Range: -7.4857
Max Act: 7.3607. Min Act: -0.1700
Data Index: 1863403 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19