Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2901 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2268. Min Range: -8.2268
Max Act: 8.2268. Min Act: -0.1700
Data Index: 1935934 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.9768. Min Act: -0.1700
Data Index: 4680051 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.9455. Min Act: -0.1700
Data Index: 7497440 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.9143. Min Act: -0.1699
Data Index: 3552905 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.8830. Min Act: -0.1700
Data Index: 2981452 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.8518. Min Act: -0.1700
Data Index: 8497717 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.8518. Min Act: -0.1700
Data Index: 2778413 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.8518. Min Act: -0.1700
Data Index: 3792966 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.8205. Min Act: -0.1700
Data Index: 3972755 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.7893. Min Act: -0.1700
Data Index: 2478898 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.8205. Min Act: -0.1700
Data Index: 2644771 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.7893. Min Act: -0.1700
Data Index: 1521635 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.7580. Min Act: -0.1700
Data Index: 4799665 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.7580. Min Act: -0.1700
Data Index: 7583356 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.7580. Min Act: -0.1700
Data Index: 3800224 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.7268. Min Act: -0.1700
Data Index: 6083189 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.6330. Min Act: -0.1700
Data Index: 5418346 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.6330. Min Act: -0.1700
Data Index: 5689786 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.6018. Min Act: -0.1700
Data Index: 7817196 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2268. Min Range: -8.2268
Max Act: 7.5705. Min Act: -0.1700
Data Index: 3622371 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19