Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5564 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.5360. Min Act: -0.1700
Data Index: 6846909 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.4110. Min Act: -0.1700
Data Index: 5110203 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.3485. Min Act: -0.1700
Data Index: 8283314 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.2547. Min Act: -0.1700
Data Index: 7732267 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.2235. Min Act: -0.1700
Data Index: 5186162 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.2235. Min Act: -0.1700
Data Index: 4982767 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.1922. Min Act: -0.1700
Data Index: 8112907 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.1922. Min Act: -0.1700
Data Index: 6568638 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.1922. Min Act: -0.1700
Data Index: 1194728 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.1610. Min Act: -0.1700
Data Index: 637919 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.1922. Min Act: -0.1700
Data Index: 2717279 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.1297. Min Act: -0.1700
Data Index: 2419653 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.0984. Min Act: -0.1700
Data Index: 2448803 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.0984. Min Act: -0.1700
Data Index: 8374849 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.0672. Min Act: -0.1700
Data Index: 6736834 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.0984. Min Act: -0.1700
Data Index: 6731090 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.0984. Min Act: -0.1700
Data Index: 5108798 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.0984. Min Act: -0.1700
Data Index: 7354636 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.0672. Min Act: -0.1700
Data Index: 349533 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5360. Min Range: -4.5360
Max Act: 4.0672. Min Act: -0.1700
Data Index: 601407 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #19