Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1872 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0201. Min Range: -4.0201
Max Act: 4.0201. Min Act: -0.1700
Data Index: 3327806 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9263. Min Act: -0.1700
Data Index: 4273741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9575. Min Act: -0.1700
Data Index: 4169101 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9575. Min Act: -0.1700
Data Index: 2073015 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9263. Min Act: -0.1700
Data Index: 391631 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9263. Min Act: -0.1700
Data Index: 8345663 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9263. Min Act: -0.1700
Data Index: 6354521 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8637. Min Act: -0.1700
Data Index: 2321050 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.9263. Min Act: -0.1700
Data Index: 2649044 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 3031760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 851489 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 5236485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 6724457 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 5296885 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 8806091 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 8824426 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 2681752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8950. Min Act: -0.1700
Data Index: 5857193 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8637. Min Act: -0.1700
Data Index: 5747494 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0201. Min Range: -4.0201
Max Act: 3.8637. Min Act: -0.1700
Data Index: 2591292 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19