Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2209 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.4433. Min Act: -0.1700
Data Index: 1462285 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.2246. Min Act: -0.1700
Data Index: 679569 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4433. Min Range: -4.4433
Max Act: 4.0058. Min Act: -0.1700
Data Index: 1043735 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8807. Min Act: -0.1700
Data Index: 5515811 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8807. Min Act: -0.1700
Data Index: 6696900 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8807. Min Act: -0.1700
Data Index: 382462 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8495. Min Act: -0.1700
Data Index: 4264886 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8495. Min Act: -0.1700
Data Index: 6342708 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8651. Min Act: -0.1700
Data Index: 2154017 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8495. Min Act: -0.1700
Data Index: 4741950 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8182. Min Act: -0.1700
Data Index: 1398953 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8338. Min Act: -0.1700
Data Index: 4513226 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.7869. Min Act: -0.1700
Data Index: 8780169 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8026. Min Act: -0.1700
Data Index: 1371067 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8026. Min Act: -0.1700
Data Index: 1988559 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.7869. Min Act: -0.1700
Data Index: 3249225 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.7869. Min Act: -0.1700
Data Index: 1606136 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.7869. Min Act: -0.1700
Data Index: 77257 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.7869. Min Act: -0.1700
Data Index: 3694991 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4433. Min Range: -4.4433
Max Act: 3.8026. Min Act: -0.1700
Data Index: 6498076 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #19