Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2942 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.9359. Min Act: -0.1700
Data Index: 1185938 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.9359. Min Act: -0.1700
Data Index: 4477276 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.8109. Min Act: -0.1700
Data Index: 3343229 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.6859. Min Act: -0.1700
Data Index: 4458873 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.6234. Min Act: -0.1700
Data Index: 3369746 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.6234. Min Act: -0.1700
Data Index: 2609042 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.5609. Min Act: -0.1700
Data Index: 4046460 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.4984. Min Act: -0.1700
Data Index: 5368459 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.5609. Min Act: -0.1700
Data Index: 4250178 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.4359. Min Act: -0.1700
Data Index: 8329310 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.4359. Min Act: -0.1700
Data Index: 891578 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.4359. Min Act: -0.1700
Data Index: 605867 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.3734. Min Act: -0.1700
Data Index: 3915604 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.3734. Min Act: -0.1700
Data Index: 3871477 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.3109. Min Act: -0.1700
Data Index: 6768180 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.2484. Min Act: -0.1700
Data Index: 1218191 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.1859. Min Act: -0.1700
Data Index: 7970932 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.2484. Min Act: -0.1700
Data Index: 272073 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.2484. Min Act: -0.1700
Data Index: 5704906 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9359. Min Range: -9.9359
Max Act: 9.1859. Min Act: -0.1700
Data Index: 332850 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19