Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4017 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2925. Min Range: -7.2925
Max Act: 7.2925. Min Act: -0.1700
Data Index: 8810453 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2925. Min Range: -7.2925
Max Act: 7.0738. Min Act: -0.1700
Data Index: 1160889 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.9488. Min Act: -0.1700
Data Index: 6499940 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.8863. Min Act: -0.1700
Data Index: 3714642 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.8550. Min Act: -0.1700
Data Index: 1494228 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.8550. Min Act: -0.1700
Data Index: 1219329 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.8550. Min Act: -0.1700
Data Index: 225899 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.7925. Min Act: -0.1700
Data Index: 5662752 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.7925. Min Act: -0.1700
Data Index: 8621424 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.7613. Min Act: -0.1700
Data Index: 3349910 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.7300. Min Act: -0.1700
Data Index: 6660693 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.6988. Min Act: -0.1700
Data Index: 2731756 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.6988. Min Act: -0.1700
Data Index: 1114521 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.6675. Min Act: -0.1700
Data Index: 214320 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.6363. Min Act: -0.1700
Data Index: 3175088 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.6363. Min Act: -0.1700
Data Index: 6855879 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.6050. Min Act: -0.1700
Data Index: 7400409 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.6050. Min Act: -0.1700
Data Index: 4537209 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.6050. Min Act: -0.1700
Data Index: 3234234 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2925. Min Range: -7.2925
Max Act: 6.5738. Min Act: -0.1700
Data Index: 8002075 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19