Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1064. Min Range: -6.1064
Max Act: 6.0751. Min Act: -0.1700
Data Index: 4530679 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1064. Min Range: -6.1064
Max Act: 6.1064. Min Act: -0.1700
Data Index: 539528 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1064. Min Range: -6.1064
Max Act: 6.0751. Min Act: -0.1700
Data Index: 5290275 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1064. Min Range: -6.1064
Max Act: 6.0439. Min Act: -0.1700
Data Index: 5223533 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1064. Min Range: -6.1064
Max Act: 6.0439. Min Act: -0.1700
Data Index: 6856594 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1064. Min Range: -6.1064
Max Act: 6.0126. Min Act: -0.1700
Data Index: 7453995 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1064. Min Range: -6.1064
Max Act: 6.0126. Min Act: -0.1700
Data Index: 3516745 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1064. Min Range: -6.1064
Max Act: 6.0126. Min Act: -0.1700
Data Index: 3496612 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.9501. Min Act: -0.1700
Data Index: 7214182 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.9501. Min Act: -0.1700
Data Index: 3306100 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.9189. Min Act: -0.1700
Data Index: 2489516 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.9189. Min Act: -0.1700
Data Index: 8287303 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.8876. Min Act: -0.1700
Data Index: 3521811 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.8876. Min Act: -0.1700
Data Index: 8686749 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.8564. Min Act: -0.1700
Data Index: 5220715 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.8251. Min Act: -0.1700
Data Index: 8413050 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.8251. Min Act: -0.1700
Data Index: 1042995 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.8251. Min Act: -0.1700
Data Index: 8784424 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.8251. Min Act: -0.1700
Data Index: 6575352 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1064. Min Range: -6.1064
Max Act: 5.7626. Min Act: -0.1700
Data Index: 1209311 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19