Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3847 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.8781. Min Act: -0.1700
Data Index: 7170672 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.6281. Min Act: -0.1700
Data Index: 6696923 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.6281. Min Act: -0.1700
Data Index: 490266 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.5656. Min Act: -0.1700
Data Index: 2156586 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.5968. Min Act: -0.1700
Data Index: 3305315 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.5343. Min Act: -0.1700
Data Index: 4953639 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.5343. Min Act: -0.1700
Data Index: 7156650 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.5343. Min Act: -0.1700
Data Index: 3954935 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4718. Min Act: -0.1700
Data Index: 668035 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4718. Min Act: -0.1700
Data Index: 1556826 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4406. Min Act: -0.1700
Data Index: 1379872 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4406. Min Act: -0.1700
Data Index: 1998479 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4093. Min Act: -0.1700
Data Index: 7516914 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4406. Min Act: -0.1700
Data Index: 8537288 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4406. Min Act: -0.1700
Data Index: 7336634 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4093. Min Act: -0.1700
Data Index: 3721193 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4093. Min Act: -0.1700
Data Index: 3525920 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4093. Min Act: -0.1700
Data Index: 4742761 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4093. Min Act: -0.1700
Data Index: 3457440 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4093. Min Act: -0.1700
Data Index: 4958821 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19