Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3366. Min Range: -7.3366
Max Act: 7.3366. Min Act: -0.1700
Data Index: 1432507 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3366. Min Range: -7.3366
Max Act: 7.1178. Min Act: -0.1700
Data Index: 8554421 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3366. Min Range: -7.3366
Max Act: 7.0553. Min Act: -0.1700
Data Index: 8657223 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3366. Min Range: -7.3366
Max Act: 7.0866. Min Act: -0.1700
Data Index: 7063150 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3366. Min Range: -7.3366
Max Act: 7.0553. Min Act: -0.1700
Data Index: 2973400 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.9928. Min Act: -0.1700
Data Index: 2067255 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.9616. Min Act: -0.1700
Data Index: 5977720 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.9616. Min Act: -0.1700
Data Index: 5246217 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.9616. Min Act: -0.1700
Data Index: 4273509 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.9303. Min Act: -0.1700
Data Index: 5846086 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.8678. Min Act: -0.1700
Data Index: 1981124 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.8678. Min Act: -0.1700
Data Index: 3903714 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.8678. Min Act: -0.1700
Data Index: 4175669 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.8678. Min Act: -0.1700
Data Index: 8278740 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.8366. Min Act: -0.1700
Data Index: 7758159 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.8678. Min Act: -0.1700
Data Index: 2876968 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.8053. Min Act: -0.1700
Data Index: 3906806 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.8053. Min Act: -0.1700
Data Index: 8352272 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.7741. Min Act: -0.1700
Data Index: 6666328 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3366. Min Range: -7.3366
Max Act: 6.7741. Min Act: -0.1700
Data Index: 8464999 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19