Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5376 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2082. Min Range: -4.2082
Max Act: 4.2082. Min Act: -0.1700
Data Index: 4508659 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2082. Min Range: -4.2082
Max Act: 4.1145. Min Act: -0.1700
Data Index: 5168924 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2082. Min Range: -4.2082
Max Act: 4.0519. Min Act: -0.1700
Data Index: 1499222 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2082. Min Range: -4.2082
Max Act: 4.0207. Min Act: -0.1700
Data Index: 2467858 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2082. Min Range: -4.2082
Max Act: 4.0207. Min Act: -0.1700
Data Index: 1565396 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2082. Min Range: -4.2082
Max Act: 4.0207. Min Act: -0.1700
Data Index: 2673537 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.9894. Min Act: -0.1700
Data Index: 4699832 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.9894. Min Act: -0.1700
Data Index: 2035624 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.9582. Min Act: -0.1700
Data Index: 7529291 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.9582. Min Act: -0.1700
Data Index: 5071542 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.9269. Min Act: -0.1700
Data Index: 1164207 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.9582. Min Act: -0.1700
Data Index: 7520356 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.8956. Min Act: -0.1700
Data Index: 3113112 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.8956. Min Act: -0.1700
Data Index: 8629559 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.9269. Min Act: -0.1700
Data Index: 2191589 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.8956. Min Act: -0.1700
Data Index: 7428408 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.8956. Min Act: -0.1700
Data Index: 1990003 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.8956. Min Act: -0.1700
Data Index: 7060312 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.8644. Min Act: -0.1700
Data Index: 4603533 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2082. Min Range: -4.2082
Max Act: 3.8644. Min Act: -0.1700
Data Index: 670752 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19