Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2465 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6035. Min Range: -6.6035
Max Act: 6.6035. Min Act: -0.1700
Data Index: 2634992 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6035. Min Range: -6.6035
Max Act: 6.0410. Min Act: -0.1700
Data Index: 8001639 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.8847. Min Act: -0.1700
Data Index: 917460 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.8847. Min Act: -0.1700
Data Index: 8649212 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.9160. Min Act: -0.1700
Data Index: 8103784 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.8535. Min Act: -0.1700
Data Index: 2854863 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.8535. Min Act: -0.1700
Data Index: 2623677 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.8222. Min Act: -0.1700
Data Index: 788080 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.8222. Min Act: -0.1700
Data Index: 5411062 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.7910. Min Act: -0.1700
Data Index: 6954571 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.7597. Min Act: -0.1700
Data Index: 1024828 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.7597. Min Act: -0.1700
Data Index: 1633344 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.7910. Min Act: -0.1700
Data Index: 6044119 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.7910. Min Act: -0.1700
Data Index: 3064381 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.7597. Min Act: -0.1700
Data Index: 2287570 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.7597. Min Act: -0.1700
Data Index: 4196483 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.6972. Min Act: -0.1700
Data Index: 3280689 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.6972. Min Act: -0.1700
Data Index: 6286425 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.6660. Min Act: -0.1700
Data Index: 6018831 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6035. Min Range: -6.6035
Max Act: 5.6660. Min Act: -0.1700
Data Index: 546183 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19