Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5238 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1232. Min Range: -6.1232
Max Act: 6.1232. Min Act: -0.1700
Data Index: 6386872 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.9045. Min Act: -0.1700
Data Index: 2659274 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.9045. Min Act: -0.1700
Data Index: 7282487 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.8732. Min Act: -0.1700
Data Index: 3405239 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.8732. Min Act: -0.1700
Data Index: 5147619 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.8107. Min Act: -0.1700
Data Index: 4865706 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.8107. Min Act: -0.1700
Data Index: 2970227 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.8107. Min Act: -0.1700
Data Index: 5318138 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.7795. Min Act: -0.1700
Data Index: 5738144 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.7482. Min Act: -0.1700
Data Index: 947719 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.7482. Min Act: -0.1700
Data Index: 6717489 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.7482. Min Act: -0.1700
Data Index: 2970230 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.7170. Min Act: -0.1700
Data Index: 6520380 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.7170. Min Act: -0.1700
Data Index: 2970229 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.7170. Min Act: -0.1700
Data Index: 5627014 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.7170. Min Act: -0.1700
Data Index: 6511992 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.6857. Min Act: -0.1700
Data Index: 4675495 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.6857. Min Act: -0.1700
Data Index: 5850370 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.7170. Min Act: -0.1700
Data Index: 5318135 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1232. Min Range: -6.1232
Max Act: 5.6545. Min Act: -0.1700
Data Index: 1307917 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19