Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 453 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.7648. Min Act: -0.1700
Data Index: 8181449 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.7475. Min Act: -0.1700
Data Index: 8144476 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.7216. Min Act: -0.1700
Data Index: 5642761 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.7129. Min Act: -0.1700
Data Index: 4159725 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.7043. Min Act: -0.1700
Data Index: 2287146 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.7043. Min Act: -0.1700
Data Index: 6339257 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6869. Min Act: -0.1700
Data Index: 39551 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6782. Min Act: -0.1700
Data Index: 5327420 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6696. Min Act: -0.1700
Data Index: 836306 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6782. Min Act: -0.1700
Data Index: 5470672 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6782. Min Act: -0.1700
Data Index: 7867624 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6696. Min Act: -0.1700
Data Index: 6751894 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6696. Min Act: -0.1699
Data Index: 6836839 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6609. Min Act: -0.1700
Data Index: 3881177 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6435. Min Act: -0.1700
Data Index: 7979915 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6522. Min Act: -0.1700
Data Index: 6909401 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6435. Min Act: -0.1700
Data Index: 2974547 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6609. Min Act: -0.1700
Data Index: 7996003 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6348. Min Act: -0.1700
Data Index: 377883 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7648. Min Range: -1.7648
Max Act: 1.6435. Min Act: -0.1700
Data Index: 3795751 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19