Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.9947. Min Act: -0.1700
Data Index: 837803 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.7760. Min Act: -0.1700
Data Index: 3777548 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.6822. Min Act: -0.1700
Data Index: 5533660 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.6197. Min Act: -0.1700
Data Index: 669589 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.4947. Min Act: -0.1700
Data Index: 3962076 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.4322. Min Act: -0.1700
Data Index: 2913088 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.3072. Min Act: -0.1700
Data Index: 343886 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.3072. Min Act: -0.1700
Data Index: 2974627 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.2760. Min Act: -0.1700
Data Index: 3400285 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.2447. Min Act: -0.1700
Data Index: 431946 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.2447. Min Act: -0.1700
Data Index: 6398707 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.2447. Min Act: -0.1700
Data Index: 7860983 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.2135. Min Act: -0.1700
Data Index: 8145659 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.2135. Min Act: -0.1700
Data Index: 5705885 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.1822. Min Act: -0.1700
Data Index: 6305588 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.1510. Min Act: -0.1700
Data Index: 5799403 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.1510. Min Act: -0.1700
Data Index: 2136115 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.1197. Min Act: -0.1700
Data Index: 1516140 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.1197. Min Act: -0.1700
Data Index: 1524140 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9947. Min Range: -5.9947
Max Act: 5.1197. Min Act: -0.1700
Data Index: 1173193 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19