Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3428 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.5163. Min Act: -0.1700
Data Index: 3336433 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.5163. Min Act: -0.1700
Data Index: 3207231 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.2663. Min Act: -0.1700
Data Index: 4165237 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.2038. Min Act: -0.1700
Data Index: 854743 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.2038. Min Act: -0.1700
Data Index: 2273869 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.1726. Min Act: -0.1700
Data Index: 5916526 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.1413. Min Act: -0.1700
Data Index: 5070838 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.1413. Min Act: -0.1700
Data Index: 3503410 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.1101. Min Act: -0.1700
Data Index: 5246973 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.0788. Min Act: -0.1700
Data Index: 6802070 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5163. Min Range: -7.5163
Max Act: 6.9851. Min Act: -0.1700
Data Index: 4842627 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.0163. Min Act: -0.1700
Data Index: 7816456 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.0163. Min Act: -0.1700
Data Index: 3232293 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.0163. Min Act: -0.1700
Data Index: 1614306 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.0163. Min Act: -0.1700
Data Index: 2870930 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5163. Min Range: -7.5163
Max Act: 7.0476. Min Act: -0.1700
Data Index: 3818825 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5163. Min Range: -7.5163
Max Act: 6.9851. Min Act: -0.1700
Data Index: 3806187 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5163. Min Range: -7.5163
Max Act: 6.9851. Min Act: -0.1700
Data Index: 2586778 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5163. Min Range: -7.5163
Max Act: 6.9226. Min Act: -0.1700
Data Index: 3728958 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5163. Min Range: -7.5163
Max Act: 6.9226. Min Act: -0.1700
Data Index: 564602 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19