Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.6588. Min Act: -0.1700
Data Index: 4434380 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5651. Min Act: -0.1700
Data Index: 4208609 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5651. Min Act: -0.1700
Data Index: 1941545 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5338. Min Act: -0.1700
Data Index: 8000792 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5651. Min Act: -0.1700
Data Index: 7767627 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5026. Min Act: -0.1700
Data Index: 675527 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5338. Min Act: -0.1700
Data Index: 6293436 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.5338. Min Act: -0.1700
Data Index: 100277 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4713. Min Act: -0.1700
Data Index: 6845345 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4713. Min Act: -0.1700
Data Index: 5921655 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4713. Min Act: -0.1700
Data Index: 2324264 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4401. Min Act: -0.1700
Data Index: 6792464 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4401. Min Act: -0.1700
Data Index: 7442339 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4401. Min Act: -0.1700
Data Index: 849175 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4401. Min Act: -0.1700
Data Index: 5553779 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4088. Min Act: -0.1700
Data Index: 3060293 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4401. Min Act: -0.1700
Data Index: 1095041 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4401. Min Act: -0.1700
Data Index: 8248283 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4088. Min Act: -0.1700
Data Index: 1982042 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6588. Min Range: -4.6588
Max Act: 4.4088. Min Act: -0.1700
Data Index: 530597 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19