Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1709 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.8689. Min Act: -0.1700
Data Index: 1336195 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.8689. Min Act: -0.1700
Data Index: 3486649 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.8432. Min Act: -0.1700
Data Index: 1689287 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.8517. Min Act: -0.1700
Data Index: 1294272 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.8432. Min Act: -0.1699
Data Index: 3292953 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7830. Min Act: -0.1700
Data Index: 4148741 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7916. Min Act: -0.1700
Data Index: 3263990 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7744. Min Act: -0.1700
Data Index: 7096370 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7744. Min Act: -0.1700
Data Index: 1471730 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7744. Min Act: -0.1700
Data Index: 7317122 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7744. Min Act: -0.1700
Data Index: 4906827 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7658. Min Act: -0.1698
Data Index: 2052615 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7744. Min Act: -0.1700
Data Index: 4107805 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7658. Min Act: -0.1700
Data Index: 7587503 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7658. Min Act: -0.1700
Data Index: 23452 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7744. Min Act: -0.1700
Data Index: 8688855 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7658. Min Act: -0.1700
Data Index: 7096375 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7658. Min Act: -0.1700
Data Index: 2192105 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7658. Min Act: -0.1700
Data Index: 847095 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8689. Min Range: -1.8689
Max Act: 1.7485. Min Act: -0.1700
Data Index: 3384369 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19