Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4637 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.8962. Min Act: -0.1700
Data Index: 2259874 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.8024. Min Act: -0.1699
Data Index: 4197763 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.8024. Min Act: -0.1699
Data Index: 4847239 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.7087. Min Act: -0.1700
Data Index: 4184552 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.7087. Min Act: -0.1700
Data Index: 4095690 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.7087. Min Act: -0.1700
Data Index: 5662482 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.6774. Min Act: -0.1700
Data Index: 8364321 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.7087. Min Act: -0.1699
Data Index: 3691200 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.6462. Min Act: -0.1700
Data Index: 8522893 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.6462. Min Act: -0.1700
Data Index: 5288148 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.6774. Min Act: -0.1700
Data Index: 2608751 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.6462. Min Act: -0.1700
Data Index: 4397412 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.6149. Min Act: -0.1700
Data Index: 5259340 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.6149. Min Act: -0.1700
Data Index: 8370516 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.5837. Min Act: -0.1700
Data Index: 5622204 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.5837. Min Act: -0.1700
Data Index: 4713089 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.5837. Min Act: -0.1700
Data Index: 6155545 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.5524. Min Act: -0.1700
Data Index: 811937 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.5524. Min Act: -0.1700
Data Index: 1669666 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8962. Min Range: -4.8962
Max Act: 4.5524. Min Act: -0.1700
Data Index: 6583084 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #19