Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2435 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.9245. Min Act: -0.1700
Data Index: 2909190 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.7995. Min Act: -0.1700
Data Index: 4570257 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.6745. Min Act: -0.1700
Data Index: 5511994 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.5808. Min Act: -0.1700
Data Index: 5085064 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.5495. Min Act: -0.1700
Data Index: 6854195 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.5495. Min Act: -0.1700
Data Index: 6849475 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.4245. Min Act: -0.1700
Data Index: 1509246 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.3933. Min Act: -0.1700
Data Index: 4905483 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.3620. Min Act: -0.1700
Data Index: 8041246 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.3620. Min Act: -0.1700
Data Index: 6283115 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.3620. Min Act: -0.1700
Data Index: 5560593 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.3308. Min Act: -0.1700
Data Index: 176988 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.2995. Min Act: -0.1700
Data Index: 1515173 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.2995. Min Act: -0.1700
Data Index: 3068367 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.2995. Min Act: -0.1700
Data Index: 1333305 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.2683. Min Act: -0.1700
Data Index: 3320125 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.2683. Min Act: -0.1700
Data Index: 7267503 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.2370. Min Act: -0.1700
Data Index: 6303074 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.2683. Min Act: -0.1700
Data Index: 168678 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9245. Min Range: -7.9245
Max Act: 7.2683. Min Act: -0.1700
Data Index: 6676217 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #19