Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1103 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1557. Min Range: -4.1557
Max Act: 4.1557. Min Act: -0.1700
Data Index: 5342157 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1557. Min Range: -4.1557
Max Act: 4.0620. Min Act: -0.1700
Data Index: 5964678 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1557. Min Range: -4.1557
Max Act: 4.0307. Min Act: -0.1700
Data Index: 73369 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1557. Min Range: -4.1557
Max Act: 4.0620. Min Act: -0.1700
Data Index: 4034566 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.9682. Min Act: -0.1700
Data Index: 4624308 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.9682. Min Act: -0.1700
Data Index: 1475290 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.9369. Min Act: -0.1700
Data Index: 4105714 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.9057. Min Act: -0.1700
Data Index: 3723544 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.9369. Min Act: -0.1700
Data Index: 3307318 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.9369. Min Act: -0.1700
Data Index: 5940686 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.9057. Min Act: -0.1700
Data Index: 6660305 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.8744. Min Act: -0.1700
Data Index: 2304363 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.8744. Min Act: -0.1700
Data Index: 1110640 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.8118. Min Act: -0.1700
Data Index: 3781480 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.8431. Min Act: -0.1700
Data Index: 2603711 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.8431. Min Act: -0.1700
Data Index: 4015680 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.8431. Min Act: -0.1700
Data Index: 8556136 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.8431. Min Act: -0.1700
Data Index: 8265024 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.7962. Min Act: -0.1700
Data Index: 2481261 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1557. Min Range: -4.1557
Max Act: 3.8431. Min Act: -0.1700
Data Index: 1660410 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19