Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 700 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0250. Min Range: -5.0250
Max Act: 5.0250. Min Act: -0.1700
Data Index: 7840732 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.9625. Min Act: -0.1700
Data Index: 172656 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.9313. Min Act: -0.1700
Data Index: 172655 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.9313. Min Act: -0.1700
Data Index: 8516058 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.9625. Min Act: -0.1700
Data Index: 2034665 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.9000. Min Act: -0.1700
Data Index: 2210742 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.8688. Min Act: -0.1700
Data Index: 78077 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.8688. Min Act: -0.1700
Data Index: 4664727 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.8375. Min Act: -0.1700
Data Index: 1464780 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.8063. Min Act: -0.1700
Data Index: 1331720 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.8063. Min Act: -0.1700
Data Index: 4246143 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.8063. Min Act: -0.1700
Data Index: 5505983 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.7750. Min Act: -0.1700
Data Index: 180879 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.7750. Min Act: -0.1700
Data Index: 211208 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.7438. Min Act: -0.1700
Data Index: 8102421 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.7438. Min Act: -0.1700
Data Index: 1283207 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.7438. Min Act: -0.1700
Data Index: 7627832 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.7438. Min Act: -0.1700
Data Index: 4515960 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.7438. Min Act: -0.1700
Data Index: 2221778 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0250. Min Range: -5.0250
Max Act: 4.7438. Min Act: -0.1700
Data Index: 1699925 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19