Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4979 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7239. Min Range: -7.7239
Max Act: 7.7239. Min Act: -0.1700
Data Index: 113391 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7239. Min Range: -7.7239
Max Act: 7.4114. Min Act: -0.1700
Data Index: 113401 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.9114. Min Act: -0.1700
Data Index: 5679425 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.7864. Min Act: -0.1700
Data Index: 445318 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.7864. Min Act: -0.1700
Data Index: 789718 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.7864. Min Act: -0.1700
Data Index: 1903135 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.6614. Min Act: -0.1700
Data Index: 917937 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.6301. Min Act: -0.1700
Data Index: 2377926 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.5989. Min Act: -0.1700
Data Index: 2454680 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.5989. Min Act: -0.1700
Data Index: 273636 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.5989. Min Act: -0.1700
Data Index: 3054645 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.5676. Min Act: -0.1700
Data Index: 8338720 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.5676. Min Act: -0.1700
Data Index: 5683686 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.5364. Min Act: -0.1700
Data Index: 8358616 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.5051. Min Act: -0.1700
Data Index: 5825873 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.4739. Min Act: -0.1700
Data Index: 3565356 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.4426. Min Act: -0.1700
Data Index: 8338730 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.4426. Min Act: -0.1700
Data Index: 8788289 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.4114. Min Act: -0.1700
Data Index: 4455842 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7239. Min Range: -7.7239
Max Act: 6.3801. Min Act: -0.1700
Data Index: 8306912 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19