Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2545 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1959. Min Act: -0.1700
Data Index: 8095279 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1959. Min Act: -0.1700
Data Index: 7240477 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1646. Min Act: -0.1700
Data Index: 5823800 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1646. Min Act: -0.1700
Data Index: 6117699 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1334. Min Act: -0.1700
Data Index: 3884082 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1334. Min Act: -0.1700
Data Index: 2378733 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1334. Min Act: -0.1700
Data Index: 6830699 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1021. Min Act: -0.1700
Data Index: 5806095 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1021. Min Act: -0.1700
Data Index: 8579406 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1021. Min Act: -0.1700
Data Index: 8071784 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1021. Min Act: -0.1700
Data Index: 6754527 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1021. Min Act: -0.1700
Data Index: 3476882 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.0708. Min Act: -0.1700
Data Index: 5898590 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.1021. Min Act: -0.1700
Data Index: 4584754 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.0708. Min Act: -0.1700
Data Index: 3725692 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.0708. Min Act: -0.1700
Data Index: 2151725 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.0708. Min Act: -0.1700
Data Index: 2168597 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.0708. Min Act: -0.1700
Data Index: 3909835 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.0708. Min Act: -0.1700
Data Index: 3968364 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1959. Min Range: -4.1959
Max Act: 4.0708. Min Act: -0.1700
Data Index: 4464559 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19