Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3757 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0072. Min Range: -3.0072
Max Act: 3.0072. Min Act: -0.1700
Data Index: 8351549 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8964. Min Act: -0.1700
Data Index: 2359518 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8964. Min Act: -0.1700
Data Index: 868984 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8806. Min Act: -0.1700
Data Index: 6907167 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8647. Min Act: -0.1700
Data Index: 1626754 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8647. Min Act: -0.1700
Data Index: 7642265 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8647. Min Act: -0.1700
Data Index: 1752053 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8806. Min Act: -0.1700
Data Index: 3602107 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8647. Min Act: -0.1700
Data Index: 8561357 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8488. Min Act: -0.1700
Data Index: 6521234 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8329. Min Act: -0.1700
Data Index: 2688705 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8329. Min Act: -0.1700
Data Index: 1866403 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8329. Min Act: -0.1700
Data Index: 7573481 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8329. Min Act: -0.1700
Data Index: 3959674 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8329. Min Act: -0.1700
Data Index: 3267466 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8329. Min Act: -0.1700
Data Index: 3243017 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8329. Min Act: -0.1700
Data Index: 4737460 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8170. Min Act: -0.1700
Data Index: 620295 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8170. Min Act: -0.1700
Data Index: 4207980 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0072. Min Range: -3.0072
Max Act: 2.8170. Min Act: -0.1700
Data Index: 2204618 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19