Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2187 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.3123. Min Act: -0.1700
Data Index: 7978196 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.2810. Min Act: -0.1700
Data Index: 2640461 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.2498. Min Act: -0.1700
Data Index: 633237 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.2185. Min Act: -0.1700
Data Index: 7083966 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.1560. Min Act: -0.1700
Data Index: 2802260 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.1248. Min Act: -0.1700
Data Index: 7450835 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.1248. Min Act: -0.1700
Data Index: 743701 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.1248. Min Act: -0.1700
Data Index: 3297201 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.1560. Min Act: -0.1700
Data Index: 5324319 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.0935. Min Act: -0.1700
Data Index: 1038994 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.0623. Min Act: -0.1700
Data Index: 3654816 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.0623. Min Act: -0.1700
Data Index: 3769420 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.0310. Min Act: -0.1700
Data Index: 4195880 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.0310. Min Act: -0.1700
Data Index: 3438345 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.0935. Min Act: -0.1700
Data Index: 6811862 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.0623. Min Act: -0.1700
Data Index: 4645458 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.0623. Min Act: -0.1700
Data Index: 652994 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.0310. Min Act: -0.1700
Data Index: 7437804 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3123. Min Range: -6.3123
Max Act: 5.9998. Min Act: -0.1700
Data Index: 3798353 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3123. Min Range: -6.3123
Max Act: 6.0623. Min Act: -0.1700
Data Index: 6122023 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19