Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5615 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.7544. Min Act: -0.1700
Data Index: 2507862 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.6919. Min Act: -0.1700
Data Index: 8498111 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.6294. Min Act: -0.1700
Data Index: 2461171 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.5669. Min Act: -0.1700
Data Index: 8619794 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.5669. Min Act: -0.1700
Data Index: 1109117 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.5044. Min Act: -0.1700
Data Index: 682822 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.4419. Min Act: -0.1700
Data Index: 6755963 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.4419. Min Act: -0.1700
Data Index: 6102186 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.4419. Min Act: -0.1700
Data Index: 4520757 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.4419. Min Act: -0.1700
Data Index: 1272824 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.4419. Min Act: -0.1700
Data Index: 209617 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.4107. Min Act: -0.1700
Data Index: 7845157 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.4107. Min Act: -0.1700
Data Index: 1957954 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.3169. Min Act: -0.1700
Data Index: 2328077 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.3482. Min Act: -0.1700
Data Index: 6222985 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.3482. Min Act: -0.1700
Data Index: 8626325 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.3482. Min Act: -0.1700
Data Index: 4879199 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.3169. Min Act: -0.1700
Data Index: 3938440 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.3169. Min Act: -0.1700
Data Index: 4650070 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7544. Min Range: -7.7544
Max Act: 7.2857. Min Act: -0.1700
Data Index: 8135776 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19