Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8843. Min Act: -0.1700
Data Index: 2850566 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8843. Min Act: -0.1700
Data Index: 5993170 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8531. Min Act: -0.1700
Data Index: 6666688 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8218. Min Act: -0.1700
Data Index: 7963379 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8218. Min Act: -0.1700
Data Index: 2134448 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8218. Min Act: -0.1700
Data Index: 607205 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.8218. Min Act: -0.1700
Data Index: 607203 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7905. Min Act: -0.1700
Data Index: 6295109 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7905. Min Act: -0.1700
Data Index: 393708 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7905. Min Act: -0.1700
Data Index: 5548944 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7905. Min Act: -0.1700
Data Index: 5993172 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7592. Min Act: -0.1700
Data Index: 4238692 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7592. Min Act: -0.1700
Data Index: 8816949 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7592. Min Act: -0.1700
Data Index: 5552843 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7280. Min Act: -0.1700
Data Index: 7758691 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.7280. Min Act: -0.1700
Data Index: 6825474 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6967. Min Act: -0.1700
Data Index: 6452522 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6654. Min Act: -0.1700
Data Index: 4350968 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6654. Min Act: -0.1700
Data Index: 2225654 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8843. Min Range: -3.8843
Max Act: 3.6654. Min Act: -0.1700
Data Index: 7466985 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #19