Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.8477. Min Act: -0.1700
Data Index: 872015 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7962. Min Act: -0.1700
Data Index: 4154620 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7790. Min Act: -0.1700
Data Index: 4989461 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7790. Min Act: -0.1700
Data Index: 2205653 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7703. Min Act: -0.1699
Data Index: 6008433 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7617. Min Act: -0.1700
Data Index: 4154621 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7531. Min Act: -0.1700
Data Index: 1553377 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7617. Min Act: -0.1700
Data Index: 3393419 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7617. Min Act: -0.1700
Data Index: 6424802 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7617. Min Act: -0.1699
Data Index: 6181012 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7617. Min Act: -0.1700
Data Index: 7866434 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7444. Min Act: -0.1700
Data Index: 6938083 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7531. Min Act: -0.1700
Data Index: 5440794 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7703. Min Act: -0.1700
Data Index: 1181984 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7531. Min Act: -0.1700
Data Index: 8245830 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7531. Min Act: -0.1700
Data Index: 5394571 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7271. Min Act: -0.1700
Data Index: 1825293 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7358. Min Act: -0.1700
Data Index: 5757750 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7358. Min Act: -0.1700
Data Index: 2379378 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8477. Min Range: -1.8477
Max Act: 1.7271. Min Act: -0.1700
Data Index: 4554153 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19