Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 414 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.8270. Min Act: -0.1700
Data Index: 5586007 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.8270. Min Act: -0.1700
Data Index: 3980992 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.7020. Min Act: -0.1700
Data Index: 5206967 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.6395. Min Act: -0.1700
Data Index: 2656606 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.5770. Min Act: -0.1700
Data Index: 8773765 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.5770. Min Act: -0.1700
Data Index: 4017363 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.6395. Min Act: -0.1700
Data Index: 8587357 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.5145. Min Act: -0.1700
Data Index: 5451670 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.5145. Min Act: -0.1700
Data Index: 1845874 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.4832. Min Act: -0.1700
Data Index: 8494571 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.4520. Min Act: -0.1700
Data Index: 3190709 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.4207. Min Act: -0.1700
Data Index: 5873041 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.3895. Min Act: -0.1700
Data Index: 3530931 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.3582. Min Act: -0.1700
Data Index: 1192770 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.3582. Min Act: -0.1700
Data Index: 2320198 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.3582. Min Act: -0.1700
Data Index: 7287853 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.3270. Min Act: -0.1700
Data Index: 504696 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.3270. Min Act: -0.1700
Data Index: 7570155 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.3582. Min Act: -0.1700
Data Index: 5085162 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8270. Min Range: -7.8270
Max Act: 7.3270. Min Act: -0.1700
Data Index: 8138080 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19