Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3292 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.5014. Min Act: -0.1700
Data Index: 2371402 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.4701. Min Act: -0.1699
Data Index: 267329 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.4389. Min Act: -0.1700
Data Index: 7897198 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.4076. Min Act: -0.1700
Data Index: 7897195 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3764. Min Act: -0.1700
Data Index: 7070806 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3764. Min Act: -0.1700
Data Index: 4641447 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3764. Min Act: -0.1700
Data Index: 8385219 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3451. Min Act: -0.1700
Data Index: 7298098 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3451. Min Act: -0.1700
Data Index: 7833203 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2826. Min Act: -0.1700
Data Index: 3178891 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3139. Min Act: -0.1700
Data Index: 7319245 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3139. Min Act: -0.1700
Data Index: 2778675 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3139. Min Act: -0.1700
Data Index: 967606 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3139. Min Act: -0.1700
Data Index: 7288089 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3139. Min Act: -0.1700
Data Index: 4163723 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2826. Min Act: -0.1700
Data Index: 3359171 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2826. Min Act: -0.1700
Data Index: 2737964 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2826. Min Act: -0.1700
Data Index: 4992749 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.2826. Min Act: -0.1700
Data Index: 7833196 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5014. Min Range: -5.5014
Max Act: 5.3139. Min Act: -0.1700
Data Index: 5154924 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19