Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2705 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.8901. Min Act: -0.1700
Data Index: 5155401 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.8901. Min Act: -0.1700
Data Index: 6115242 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.8589. Min Act: -0.1700
Data Index: 2187965 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7964. Min Act: -0.1700
Data Index: 7821341 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7964. Min Act: -0.1700
Data Index: 6776695 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.8276. Min Act: -0.1700
Data Index: 7198371 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7651. Min Act: -0.1700
Data Index: 4056399 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7651. Min Act: -0.1697
Data Index: 2483910 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7339. Min Act: -0.1700
Data Index: 7066778 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7026. Min Act: -0.1700
Data Index: 6134526 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7026. Min Act: -0.1700
Data Index: 3023756 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7026. Min Act: -0.1700
Data Index: 7683669 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7026. Min Act: -0.1700
Data Index: 5953153 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.6714. Min Act: -0.1700
Data Index: 1988449 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7026. Min Act: -0.1699
Data Index: 3812200 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7026. Min Act: -0.1699
Data Index: 7471149 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.7026. Min Act: -0.1700
Data Index: 4429931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.6401. Min Act: -0.1700
Data Index: 5763621 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.6714. Min Act: -0.1700
Data Index: 8120639 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8901. Min Range: -5.8901
Max Act: 5.6714. Min Act: -0.1699
Data Index: 877181 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19