Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 985 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.5644. Min Act: -0.1700
Data Index: 8826160 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.5331. Min Act: -0.1700
Data Index: 4809300 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.5331. Min Act: -0.1700
Data Index: 4184566 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.5331. Min Act: -0.1700
Data Index: 2951718 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.5331. Min Act: -0.1700
Data Index: 4855065 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.5019. Min Act: -0.1700
Data Index: 2654778 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.5019. Min Act: -0.1700
Data Index: 4855063 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4706. Min Act: -0.1700
Data Index: 2791662 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4706. Min Act: -0.1700
Data Index: 2596589 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.5019. Min Act: -0.1700
Data Index: 7905243 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4394. Min Act: -0.1700
Data Index: 3287754 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4394. Min Act: -0.1700
Data Index: 3936288 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4394. Min Act: -0.1700
Data Index: 8115788 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4394. Min Act: -0.1700
Data Index: 7949586 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4394. Min Act: -0.1700
Data Index: 2441147 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4706. Min Act: -0.1700
Data Index: 2654776 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4394. Min Act: -0.1700
Data Index: 630455 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4706. Min Act: -0.1700
Data Index: 322192 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4394. Min Act: -0.1700
Data Index: 2822091 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5644. Min Range: -4.5644
Max Act: 4.4394. Min Act: -0.1700
Data Index: 6094354 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19