Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 613 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.6384. Min Act: -0.1700
Data Index: 108646 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.5901. Min Act: -0.1700
Data Index: 6861803 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.5740. Min Act: -0.1700
Data Index: 2437627 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.5094. Min Act: -0.1700
Data Index: 6861808 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4932. Min Act: -0.1700
Data Index: 4141811 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4932. Min Act: -0.1700
Data Index: 108647 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4770. Min Act: -0.1700
Data Index: 7388283 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4770. Min Act: -0.1700
Data Index: 2294657 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4607. Min Act: -0.1700
Data Index: 8379336 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4607. Min Act: -0.1700
Data Index: 8751492 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4607. Min Act: -0.1700
Data Index: 6861802 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4607. Min Act: -0.1700
Data Index: 5003631 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4607. Min Act: -0.1700
Data Index: 6661329 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4445. Min Act: -0.1700
Data Index: 6861806 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4282. Min Act: -0.1700
Data Index: 5439577 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4282. Min Act: -0.1700
Data Index: 108642 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4282. Min Act: -0.1700
Data Index: 5854442 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4282. Min Act: -0.1700
Data Index: 513211 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4282. Min Act: -0.1700
Data Index: 3306275 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6384. Min Range: -2.6384
Max Act: 2.4119. Min Act: -0.1700
Data Index: 7859218 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19