Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1889 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2786. Min Range: -3.2786
Max Act: 3.2786. Min Act: -0.1700
Data Index: 7783787 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2786. Min Range: -3.2786
Max Act: 3.1529. Min Act: -0.1700
Data Index: 3906104 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2786. Min Range: -3.2786
Max Act: 3.1371. Min Act: -0.1700
Data Index: 8149462 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2786. Min Range: -3.2786
Max Act: 3.0741. Min Act: -0.1700
Data Index: 4289641 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2786. Min Range: -3.2786
Max Act: 3.0425. Min Act: -0.1700
Data Index: 1263961 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2786. Min Range: -3.2786
Max Act: 3.0425. Min Act: -0.1700
Data Index: 3019025 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2786. Min Range: -3.2786
Max Act: 3.0425. Min Act: -0.1700
Data Index: 5920538 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2786. Min Range: -3.2786
Max Act: 3.0109. Min Act: -0.1700
Data Index: 8279146 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9793. Min Act: -0.1700
Data Index: 3107790 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9951. Min Act: -0.1700
Data Index: 5635000 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9951. Min Act: -0.1700
Data Index: 2003876 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9951. Min Act: -0.1700
Data Index: 6567798 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9635. Min Act: -0.1700
Data Index: 3840106 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9477. Min Act: -0.1700
Data Index: 5907777 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9477. Min Act: -0.1700
Data Index: 1328788 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9318. Min Act: -0.1700
Data Index: 5321083 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9318. Min Act: -0.1700
Data Index: 4829543 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9318. Min Act: -0.1700
Data Index: 8130831 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9001. Min Act: -0.1700
Data Index: 6349066 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2786. Min Range: -3.2786
Max Act: 2.9001. Min Act: -0.1700
Data Index: 156273 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19