Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.9218. Min Act: -0.1700
Data Index: 6508122 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.8280. Min Act: -0.1700
Data Index: 5650197 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.8280. Min Act: -0.1700
Data Index: 831485 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7968. Min Act: -0.1700
Data Index: 6962315 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7968. Min Act: -0.1700
Data Index: 8312747 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7655. Min Act: -0.1700
Data Index: 7075306 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7655. Min Act: -0.1700
Data Index: 4037601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7655. Min Act: -0.1700
Data Index: 8800958 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7343. Min Act: -0.1700
Data Index: 6605696 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7343. Min Act: -0.1700
Data Index: 493756 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7343. Min Act: -0.1700
Data Index: 5308972 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7343. Min Act: -0.1700
Data Index: 4175003 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7343. Min Act: -0.1700
Data Index: 8661860 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7343. Min Act: -0.1700
Data Index: 8381381 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7343. Min Act: -0.1700
Data Index: 1767068 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7343. Min Act: -0.1700
Data Index: 7606553 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7343. Min Act: -0.1700
Data Index: 3160397 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7655. Min Act: -0.1700
Data Index: 2855303 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7030. Min Act: -0.1700
Data Index: 1021438 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9218. Min Range: -4.9218
Max Act: 4.7030. Min Act: -0.1700
Data Index: 1750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19