Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1701 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.4016. Min Act: -0.1700
Data Index: 6986720 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.3703. Min Act: -0.1700
Data Index: 6037234 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.3078. Min Act: -0.1700
Data Index: 7415774 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.2141. Min Act: -0.1700
Data Index: 1120149 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.2141. Min Act: -0.1700
Data Index: 6093486 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1828. Min Act: -0.1700
Data Index: 5852260 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1828. Min Act: -0.1700
Data Index: 3218100 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1828. Min Act: -0.1700
Data Index: 782632 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.1516. Min Act: -0.1700
Data Index: 4226303 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.0578. Min Act: -0.1700
Data Index: 3517833 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.0266. Min Act: -0.1700
Data Index: 24425 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4016. Min Range: -5.4016
Max Act: 5.0266. Min Act: -0.1700
Data Index: 6618051 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9953. Min Act: -0.1700
Data Index: 4273325 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9953. Min Act: -0.1700
Data Index: 4667349 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9953. Min Act: -0.1700
Data Index: 1079074 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9328. Min Act: -0.1700
Data Index: 5368942 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9016. Min Act: -0.1700
Data Index: 7520953 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9016. Min Act: -0.1700
Data Index: 4767751 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9016. Min Act: -0.1700
Data Index: 6945568 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4016. Min Range: -5.4016
Max Act: 4.9016. Min Act: -0.1700
Data Index: 161808 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19