Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2355 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2066. Min Range: -5.2066
Max Act: 5.2066. Min Act: -0.1700
Data Index: 8044292 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2066. Min Range: -5.2066
Max Act: 5.1441. Min Act: -0.1700
Data Index: 7132532 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2066. Min Range: -5.2066
Max Act: 5.0816. Min Act: -0.1700
Data Index: 419099 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2066. Min Range: -5.2066
Max Act: 5.0503. Min Act: -0.1700
Data Index: 4401449 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2066. Min Range: -5.2066
Max Act: 5.0191. Min Act: -0.1700
Data Index: 7036680 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.9878. Min Act: -0.1700
Data Index: 2305444 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.9878. Min Act: -0.1700
Data Index: 6249670 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.9878. Min Act: -0.1700
Data Index: 8499590 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2066. Min Range: -5.2066
Max Act: 5.0191. Min Act: -0.1700
Data Index: 5007114 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8941. Min Act: -0.1700
Data Index: 4161856 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8941. Min Act: -0.1700
Data Index: 266387 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8941. Min Act: -0.1700
Data Index: 6020431 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8941. Min Act: -0.1700
Data Index: 7972214 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8628. Min Act: -0.1700
Data Index: 4420036 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8628. Min Act: -0.1700
Data Index: 465882 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8628. Min Act: -0.1700
Data Index: 3864917 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8628. Min Act: -0.1700
Data Index: 8659989 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8316. Min Act: -0.1700
Data Index: 7844424 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8316. Min Act: -0.1700
Data Index: 433644 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2066. Min Range: -5.2066
Max Act: 4.8003. Min Act: -0.1700
Data Index: 6623129 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19