Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3680 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.4756. Min Act: -0.1700
Data Index: 2598085 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.3506. Min Act: -0.1700
Data Index: 3448746 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.3506. Min Act: -0.1700
Data Index: 2766972 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.3506. Min Act: -0.1699
Data Index: 3772205 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.2881. Min Act: -0.1700
Data Index: 404383 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.2881. Min Act: -0.1700
Data Index: 69476 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.1318. Min Act: -0.1700
Data Index: 4684304 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.1318. Min Act: -0.1700
Data Index: 5799381 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.1006. Min Act: -0.1700
Data Index: 326257 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.0381. Min Act: -0.1700
Data Index: 2479347 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.0381. Min Act: -0.1700
Data Index: 4179308 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4756. Min Range: -8.4756
Max Act: 8.0068. Min Act: -0.1700
Data Index: 3049346 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4756. Min Range: -8.4756
Max Act: 7.8818. Min Act: -0.1700
Data Index: 1043614 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4756. Min Range: -8.4756
Max Act: 7.9131. Min Act: -0.1700
Data Index: 7698001 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4756. Min Range: -8.4756
Max Act: 7.9131. Min Act: -0.1700
Data Index: 6549488 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4756. Min Range: -8.4756
Max Act: 7.9131. Min Act: -0.1700
Data Index: 6032067 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4756. Min Range: -8.4756
Max Act: 7.9131. Min Act: -0.1700
Data Index: 5560479 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4756. Min Range: -8.4756
Max Act: 7.8818. Min Act: -0.1700
Data Index: 542122 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4756. Min Range: -8.4756
Max Act: 7.8506. Min Act: -0.1700
Data Index: 3733856 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4756. Min Range: -8.4756
Max Act: 7.8193. Min Act: -0.1700
Data Index: 1560322 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #19