Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4314 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2047. Min Range: -6.2047
Max Act: 6.2047. Min Act: -0.1700
Data Index: 5998765 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.7360. Min Act: -0.1700
Data Index: 968401 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.7047. Min Act: -0.1700
Data Index: 6284601 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.5485. Min Act: -0.1700
Data Index: 4295966 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.5172. Min Act: -0.1700
Data Index: 5914205 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.4860. Min Act: -0.1700
Data Index: 6441237 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.4547. Min Act: -0.1700
Data Index: 7376188 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.4235. Min Act: -0.1700
Data Index: 5117816 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.3922. Min Act: -0.1700
Data Index: 3393771 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.3610. Min Act: -0.1700
Data Index: 7161312 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.3610. Min Act: -0.1700
Data Index: 5878672 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.2985. Min Act: -0.1700
Data Index: 4209028 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.2985. Min Act: -0.1700
Data Index: 7686148 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.2985. Min Act: -0.1700
Data Index: 5146684 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.2985. Min Act: -0.1700
Data Index: 7434616 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.3297. Min Act: -0.1700
Data Index: 3341996 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.2985. Min Act: -0.1700
Data Index: 3639433 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.2985. Min Act: -0.1700
Data Index: 646402 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.2985. Min Act: -0.1700
Data Index: 4752249 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2047. Min Range: -6.2047
Max Act: 5.2985. Min Act: -0.1700
Data Index: 2540613 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19