Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1768 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.5474. Min Act: -0.1700
Data Index: 74648 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.4537. Min Act: -0.1700
Data Index: 6649298 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.3912. Min Act: -0.1700
Data Index: 7374617 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.3287. Min Act: -0.1700
Data Index: 7991661 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.2974. Min Act: -0.1700
Data Index: 5277439 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.2662. Min Act: -0.1700
Data Index: 2680939 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.2349. Min Act: -0.1700
Data Index: 737303 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.2662. Min Act: -0.1700
Data Index: 6636301 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.2037. Min Act: -0.1700
Data Index: 5776695 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.2037. Min Act: -0.1700
Data Index: 2346944 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.1724. Min Act: -0.1700
Data Index: 5363137 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.1724. Min Act: -0.1700
Data Index: 5015485 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.1412. Min Act: -0.1700
Data Index: 5175598 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.1099. Min Act: -0.1700
Data Index: 8430547 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.1099. Min Act: -0.1700
Data Index: 6346700 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.1412. Min Act: -0.1700
Data Index: 96564 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.1099. Min Act: -0.1700
Data Index: 135822 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.0786. Min Act: -0.1700
Data Index: 8003664 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.0786. Min Act: -0.1700
Data Index: 3601615 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5474. Min Range: -4.5474
Max Act: 4.0786. Min Act: -0.1700
Data Index: 7026035 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19