Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3921 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1599. Min Range: -5.1599
Max Act: 5.1599. Min Act: -0.1700
Data Index: 830288 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1599. Min Range: -5.1599
Max Act: 5.1287. Min Act: -0.1700
Data Index: 5525018 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.9724. Min Act: -0.1700
Data Index: 3835305 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.9724. Min Act: -0.1700
Data Index: 2662689 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.9412. Min Act: -0.1700
Data Index: 5408785 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.9724. Min Act: -0.1700
Data Index: 6953085 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.9412. Min Act: -0.1700
Data Index: 3523963 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.9412. Min Act: -0.1700
Data Index: 5006071 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.9099. Min Act: -0.1700
Data Index: 3923343 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.9099. Min Act: -0.1700
Data Index: 1757719 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.9099. Min Act: -0.1700
Data Index: 2249215 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.9099. Min Act: -0.1700
Data Index: 2612871 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.8787. Min Act: -0.1700
Data Index: 4947449 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.8787. Min Act: -0.1700
Data Index: 8510901 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.8787. Min Act: -0.1700
Data Index: 1142494 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.8474. Min Act: -0.1700
Data Index: 2994937 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.8787. Min Act: -0.1700
Data Index: 2073188 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.8787. Min Act: -0.1700
Data Index: 6822045 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.8787. Min Act: -0.1700
Data Index: 244182 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1599. Min Range: -5.1599
Max Act: 4.8474. Min Act: -0.1700
Data Index: 824810 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19