Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1271 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.5241. Min Act: -0.1700
Data Index: 1011896 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.4616. Min Act: -0.1700
Data Index: 8660552 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.4304. Min Act: -0.1700
Data Index: 1226417 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.4616. Min Act: -0.1700
Data Index: 1563035 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.4616. Min Act: -0.1700
Data Index: 4535220 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.3679. Min Act: -0.1700
Data Index: 243495 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.3366. Min Act: -0.1700
Data Index: 93079 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.3366. Min Act: -0.1700
Data Index: 2574064 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.3054. Min Act: -0.1700
Data Index: 7046523 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.3054. Min Act: -0.1700
Data Index: 7252873 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.2741. Min Act: -0.1700
Data Index: 6813776 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.2116. Min Act: -0.1700
Data Index: 79115 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.2116. Min Act: -0.1700
Data Index: 3481221 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.1804. Min Act: -0.1700
Data Index: 1226416 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.1491. Min Act: -0.1700
Data Index: 4514236 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.1179. Min Act: -0.1700
Data Index: 6471133 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.0866. Min Act: -0.1700
Data Index: 4467497 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.0554. Min Act: -0.1700
Data Index: 1274550 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.0554. Min Act: -0.1700
Data Index: 4243333 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5241. Min Range: -7.5241
Max Act: 7.0241. Min Act: -0.1700
Data Index: 5976171 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19