Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 295 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.6009. Min Act: -0.1700
Data Index: 296040 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.5071. Min Act: -0.1700
Data Index: 6226963 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.5071. Min Act: -0.1700
Data Index: 3074313 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.4134. Min Act: -0.1700
Data Index: 6688567 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.4134. Min Act: -0.1700
Data Index: 2183615 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.3509. Min Act: -0.1700
Data Index: 587888 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.3196. Min Act: -0.1700
Data Index: 5639712 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.3196. Min Act: -0.1700
Data Index: 2896322 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.3196. Min Act: -0.1700
Data Index: 6333491 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.3196. Min Act: -0.1700
Data Index: 3294219 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.3196. Min Act: -0.1700
Data Index: 4450748 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.2884. Min Act: -0.1700
Data Index: 50168 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.2884. Min Act: -0.1700
Data Index: 4146106 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.2571. Min Act: -0.1700
Data Index: 7357314 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.2884. Min Act: -0.1700
Data Index: 360880 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.1634. Min Act: -0.1700
Data Index: 7219281 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.1321. Min Act: -0.1700
Data Index: 3389180 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.1634. Min Act: -0.1700
Data Index: 5953443 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.1009. Min Act: -0.1700
Data Index: 6443263 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6009. Min Range: -7.6009
Max Act: 7.1321. Min Act: -0.1700
Data Index: 4333132 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19