Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5646 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.6915. Min Act: -0.1700
Data Index: 242039 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.7228. Min Act: -0.1700
Data Index: 3045743 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.6915. Min Act: -0.1700
Data Index: 260163 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.6603. Min Act: -0.1700
Data Index: 3546078 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.6290. Min Act: -0.1700
Data Index: 8171501 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5978. Min Act: -0.1700
Data Index: 4171315 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5665. Min Act: -0.1700
Data Index: 4220087 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5665. Min Act: -0.1700
Data Index: 5429955 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5665. Min Act: -0.1700
Data Index: 5830793 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5353. Min Act: -0.1700
Data Index: 7709059 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5353. Min Act: -0.1700
Data Index: 2117037 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5040. Min Act: -0.1700
Data Index: 1392640 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5353. Min Act: -0.1700
Data Index: 8243529 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5353. Min Act: -0.1700
Data Index: 7857331 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5353. Min Act: -0.1700
Data Index: 2827962 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5353. Min Act: -0.1700
Data Index: 5221830 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5040. Min Act: -0.1700
Data Index: 7580170 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5040. Min Act: -0.1700
Data Index: 6017224 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.4728. Min Act: -0.1700
Data Index: 2432220 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7228. Min Range: -4.7228
Max Act: 4.5040. Min Act: -0.1700
Data Index: 4056154 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19