Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3185 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.7723. Min Act: -0.1700
Data Index: 3424255 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.7723. Min Act: -0.1700
Data Index: 4556410 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.7410. Min Act: -0.1700
Data Index: 7386305 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6785. Min Act: -0.1700
Data Index: 3344662 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6785. Min Act: -0.1700
Data Index: 4153840 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6785. Min Act: -0.1700
Data Index: 8545716 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6785. Min Act: -0.1700
Data Index: 2902712 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.7098. Min Act: -0.1700
Data Index: 4881406 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6785. Min Act: -0.1700
Data Index: 5453472 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6160. Min Act: -0.1700
Data Index: 5892887 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6785. Min Act: -0.1700
Data Index: 5246154 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6160. Min Act: -0.1700
Data Index: 1412874 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6160. Min Act: -0.1700
Data Index: 3564066 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6473. Min Act: -0.1700
Data Index: 3413512 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.5848. Min Act: -0.1700
Data Index: 3201567 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6160. Min Act: -0.1700
Data Index: 953076 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6160. Min Act: -0.1700
Data Index: 6293526 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6160. Min Act: -0.1700
Data Index: 444304 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.5848. Min Act: -0.1700
Data Index: 4923272 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7723. Min Range: -5.7723
Max Act: 5.6473. Min Act: -0.1700
Data Index: 8550695 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19