Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 848 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7884. Min Act: -0.1700
Data Index: 2653742 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7970. Min Act: -0.1700
Data Index: 7566612 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7884. Min Act: -0.1700
Data Index: 2256984 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7798. Min Act: -0.1700
Data Index: 4883070 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7712. Min Act: -0.1700
Data Index: 6772007 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7712. Min Act: -0.1700
Data Index: 616771 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7712. Min Act: -0.1700
Data Index: 4653845 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7712. Min Act: -0.1700
Data Index: 8420897 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7712. Min Act: -0.1700
Data Index: 8448115 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7539. Min Act: -0.1700
Data Index: 1045875 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7453. Min Act: -0.1700
Data Index: 1590394 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7193. Min Act: -0.1700
Data Index: 7138211 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7366. Min Act: -0.1700
Data Index: 2660639 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7280. Min Act: -0.1699
Data Index: 5037800 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7280. Min Act: -0.1700
Data Index: 3206861 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7366. Min Act: -0.1700
Data Index: 1740138 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7280. Min Act: -0.1700
Data Index: 6456940 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7193. Min Act: -0.1700
Data Index: 5004391 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7107. Min Act: -0.1700
Data Index: 848623 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7970. Min Range: -1.7970
Max Act: 1.7193. Min Act: -0.1700
Data Index: 6462727 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19