Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2766 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0804. Min Range: -5.0804
Max Act: 5.0804. Min Act: -0.1700
Data Index: 8032955 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.8929. Min Act: -0.1700
Data Index: 3458846 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.8929. Min Act: -0.1700
Data Index: 5754983 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.8929. Min Act: -0.1700
Data Index: 3969724 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7992. Min Act: -0.1700
Data Index: 5670115 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.8304. Min Act: -0.1700
Data Index: 3710035 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.8304. Min Act: -0.1700
Data Index: 5889100 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7992. Min Act: -0.1700
Data Index: 5769904 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7992. Min Act: -0.1700
Data Index: 1082062 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7992. Min Act: -0.1700
Data Index: 3208111 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7992. Min Act: -0.1700
Data Index: 2913808 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7992. Min Act: -0.1700
Data Index: 5515532 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7679. Min Act: -0.1700
Data Index: 2796709 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7679. Min Act: -0.1700
Data Index: 5556352 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7679. Min Act: -0.1700
Data Index: 1741289 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7679. Min Act: -0.1700
Data Index: 4487269 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7679. Min Act: -0.1700
Data Index: 7703523 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7679. Min Act: -0.1700
Data Index: 3263865 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7679. Min Act: -0.1700
Data Index: 4032370 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0804. Min Range: -5.0804
Max Act: 4.7679. Min Act: -0.1700
Data Index: 4003487 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19