Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0711. Min Range: -4.0711
Max Act: 4.0711. Min Act: -0.1700
Data Index: 6031082 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.9147. Min Act: -0.1700
Data Index: 5014758 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7584. Min Act: -0.1700
Data Index: 2964263 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7584. Min Act: -0.1700
Data Index: 6244543 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7897. Min Act: -0.1700
Data Index: 4352478 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7584. Min Act: -0.1700
Data Index: 1342419 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7584. Min Act: -0.1700
Data Index: 5908977 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7584. Min Act: -0.1700
Data Index: 2014992 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7897. Min Act: -0.1700
Data Index: 685476 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7584. Min Act: -0.1700
Data Index: 8537653 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7271. Min Act: -0.1700
Data Index: 7723649 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7271. Min Act: -0.1700
Data Index: 5363674 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7271. Min Act: -0.1700
Data Index: 5925697 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7271. Min Act: -0.1700
Data Index: 5091500 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.6958. Min Act: -0.1700
Data Index: 4247725 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7271. Min Act: -0.1700
Data Index: 6354664 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7271. Min Act: -0.1700
Data Index: 5007285 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.6958. Min Act: -0.1700
Data Index: 1039608 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.7584. Min Act: -0.1700
Data Index: 442179 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0711. Min Range: -4.0711
Max Act: 3.6958. Min Act: -0.1700
Data Index: 6488488 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19