Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4008 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1584. Min Range: -9.1584
Max Act: 9.1584. Min Act: -0.1700
Data Index: 558268 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1584. Min Range: -9.1584
Max Act: 9.0959. Min Act: -0.1700
Data Index: 3421525 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1584. Min Range: -9.1584
Max Act: 9.0334. Min Act: -0.1700
Data Index: 602289 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1584. Min Range: -9.1584
Max Act: 9.0334. Min Act: -0.1700
Data Index: 6170987 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.9709. Min Act: -0.1700
Data Index: 2561098 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.9709. Min Act: -0.1700
Data Index: 4495224 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.8459. Min Act: -0.1700
Data Index: 5218996 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.9084. Min Act: -0.1700
Data Index: 5725958 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.9084. Min Act: -0.1700
Data Index: 5002936 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.9084. Min Act: -0.1700
Data Index: 3823515 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.8459. Min Act: -0.1700
Data Index: 5952094 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.7834. Min Act: -0.1700
Data Index: 6916450 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.7834. Min Act: -0.1700
Data Index: 205402 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.7209. Min Act: -0.1700
Data Index: 5090560 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.7209. Min Act: -0.1700
Data Index: 705700 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.7209. Min Act: -0.1700
Data Index: 6368713 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.6584. Min Act: -0.1700
Data Index: 4006590 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.6584. Min Act: -0.1700
Data Index: 1022860 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.6584. Min Act: -0.1700
Data Index: 2491257 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1584. Min Range: -9.1584
Max Act: 8.6584. Min Act: -0.1700
Data Index: 6244642 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19