Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 618 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2216. Min Range: -6.2216
Max Act: 6.2216. Min Act: -0.1700
Data Index: 4950855 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2216. Min Range: -6.2216
Max Act: 6.2216. Min Act: -0.1700
Data Index: 3824198 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2216. Min Range: -6.2216
Max Act: 6.1904. Min Act: -0.1700
Data Index: 650768 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.9404. Min Act: -0.1700
Data Index: 8006440 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.9091. Min Act: -0.1700
Data Index: 8348260 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.8779. Min Act: -0.1700
Data Index: 5939128 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.8154. Min Act: -0.1700
Data Index: 8244227 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.8154. Min Act: -0.1700
Data Index: 3943089 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.8154. Min Act: -0.1700
Data Index: 2475260 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.7841. Min Act: -0.1700
Data Index: 1523389 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.7841. Min Act: -0.1700
Data Index: 6282675 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.7841. Min Act: -0.1700
Data Index: 441955 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.7841. Min Act: -0.1700
Data Index: 7162244 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.7216. Min Act: -0.1700
Data Index: 5981234 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.7216. Min Act: -0.1700
Data Index: 8449434 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.6904. Min Act: -0.1700
Data Index: 7087262 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.6591. Min Act: -0.1700
Data Index: 5181188 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.6904. Min Act: -0.1700
Data Index: 5087526 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.6904. Min Act: -0.1700
Data Index: 1991563 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2216. Min Range: -6.2216
Max Act: 5.6904. Min Act: -0.1700
Data Index: 513784 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19