Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5160 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6144. Min Range: -10.6144
Max Act: 10.6144. Min Act: -0.1700
Data Index: 7008148 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6144. Min Range: -10.6144
Max Act: 10.1769. Min Act: -0.1700
Data Index: 3949916 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6144. Min Range: -10.6144
Max Act: 10.1144. Min Act: -0.1700
Data Index: 4600910 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6144. Min Range: -10.6144
Max Act: 10.0519. Min Act: -0.1700
Data Index: 1623149 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.9269. Min Act: -0.1700
Data Index: 1983454 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.8019. Min Act: -0.1700
Data Index: 8476149 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.7394. Min Act: -0.1700
Data Index: 1185362 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.7394. Min Act: -0.1700
Data Index: 893038 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6769. Min Act: -0.1700
Data Index: 77942 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6769. Min Act: -0.1700
Data Index: 2109144 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6144. Min Act: -0.1700
Data Index: 5854007 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6769. Min Act: -0.1700
Data Index: 4462003 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6769. Min Act: -0.1700
Data Index: 7113246 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6769. Min Act: -0.1700
Data Index: 2635255 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6144. Min Act: -0.1700
Data Index: 234254 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6144. Min Act: -0.1700
Data Index: 2735170 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6144. Min Act: -0.1700
Data Index: 7390318 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6144. Min Act: -0.1700
Data Index: 3602270 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6144. Min Act: -0.1700
Data Index: 5728286 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6144. Min Range: -10.6144
Max Act: 9.6144. Min Act: -0.1700
Data Index: 6866942 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19