Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5934 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.9726. Min Act: -0.1700
Data Index: 2965969 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.8789. Min Act: -0.1700
Data Index: 826877 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.8476. Min Act: -0.1700
Data Index: 1058328 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.8476. Min Act: -0.1700
Data Index: 8429142 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.8164. Min Act: -0.1700
Data Index: 6219905 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.7851. Min Act: -0.1700
Data Index: 8027236 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.8164. Min Act: -0.1700
Data Index: 1987291 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.7851. Min Act: -0.1700
Data Index: 354954 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.7226. Min Act: -0.1700
Data Index: 2675529 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.7539. Min Act: -0.1700
Data Index: 7493420 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.6601. Min Act: -0.1700
Data Index: 4504391 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.6289. Min Act: -0.1700
Data Index: 4319592 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.6289. Min Act: -0.1700
Data Index: 7117692 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.5976. Min Act: -0.1700
Data Index: 3544162 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.5664. Min Act: -0.1700
Data Index: 5619623 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.5664. Min Act: -0.1700
Data Index: 4132459 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.5664. Min Act: -0.1700
Data Index: 935845 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.5351. Min Act: -0.1700
Data Index: 1878868 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.5039. Min Act: -0.1700
Data Index: 2945610 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9726. Min Range: -4.9726
Max Act: 4.5039. Min Act: -0.1700
Data Index: 1154677 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19