Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.6386. Min Act: -0.1700
Data Index: 1117869 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.6386. Min Act: -0.1700
Data Index: 3193373 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.5761. Min Act: -0.1700
Data Index: 6276246 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.5448. Min Act: -0.1700
Data Index: 4011189 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.5136. Min Act: -0.1700
Data Index: 4420416 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.4823. Min Act: -0.1700
Data Index: 213629 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.4823. Min Act: -0.1700
Data Index: 929930 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.4511. Min Act: -0.1700
Data Index: 445925 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.4198. Min Act: -0.1700
Data Index: 6032196 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.4511. Min Act: -0.1700
Data Index: 1567555 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.4511. Min Act: -0.1700
Data Index: 4163088 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.4511. Min Act: -0.1700
Data Index: 8472387 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.4511. Min Act: -0.1700
Data Index: 6994456 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.4198. Min Act: -0.1700
Data Index: 7271789 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.3886. Min Act: -0.1700
Data Index: 308467 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.3886. Min Act: -0.1700
Data Index: 4163089 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.3886. Min Act: -0.1700
Data Index: 4163087 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.3573. Min Act: -0.1700
Data Index: 5344005 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.3573. Min Act: -0.1700
Data Index: 7524910 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6386. Min Range: -4.6386
Max Act: 4.3573. Min Act: -0.1700
Data Index: 7448247 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19