Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0119. Min Range: -6.0119
Max Act: 6.0119. Min Act: -0.1700
Data Index: 5862815 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.8869. Min Act: -0.1700
Data Index: 2127570 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.6682. Min Act: -0.1700
Data Index: 3946370 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.6994. Min Act: -0.1700
Data Index: 3036197 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.6682. Min Act: -0.1700
Data Index: 1827259 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.6057. Min Act: -0.1700
Data Index: 2883400 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.6057. Min Act: -0.1700
Data Index: 66904 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5744. Min Act: -0.1700
Data Index: 6691418 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5744. Min Act: -0.1700
Data Index: 4370367 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5432. Min Act: -0.1700
Data Index: 3414046 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5432. Min Act: -0.1700
Data Index: 2840795 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5432. Min Act: -0.1700
Data Index: 5509024 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5119. Min Act: -0.1700
Data Index: 5235242 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5119. Min Act: -0.1700
Data Index: 8502856 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5119. Min Act: -0.1700
Data Index: 3209385 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5119. Min Act: -0.1700
Data Index: 2489373 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5119. Min Act: -0.1700
Data Index: 2096963 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.5119. Min Act: -0.1700
Data Index: 5697344 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.4182. Min Act: -0.1700
Data Index: 6095038 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0119. Min Range: -6.0119
Max Act: 5.4182. Min Act: -0.1700
Data Index: 3697360 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19