Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 949 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2213. Min Range: -7.2213
Max Act: 7.2213. Min Act: -0.1700
Data Index: 1442022 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2213. Min Range: -7.2213
Max Act: 7.2213. Min Act: -0.1700
Data Index: 1779072 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.8150. Min Act: -0.1700
Data Index: 6791512 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.7838. Min Act: -0.1700
Data Index: 5716392 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.8150. Min Act: -0.1700
Data Index: 1038025 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.7838. Min Act: -0.1700
Data Index: 5480091 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.6900. Min Act: -0.1700
Data Index: 2211384 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.6588. Min Act: -0.1700
Data Index: 638355 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.5963. Min Act: -0.1700
Data Index: 8830072 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.5650. Min Act: -0.1700
Data Index: 3850070 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.5650. Min Act: -0.1700
Data Index: 4320174 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.5338. Min Act: -0.1700
Data Index: 16661 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.5025. Min Act: -0.1700
Data Index: 1325258 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.4713. Min Act: -0.1700
Data Index: 4667498 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.4713. Min Act: -0.1700
Data Index: 2183338 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.4400. Min Act: -0.1700
Data Index: 1400444 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.4088. Min Act: -0.1700
Data Index: 503793 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.4088. Min Act: -0.1700
Data Index: 1485949 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.4088. Min Act: -0.1700
Data Index: 3173705 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2213. Min Range: -7.2213
Max Act: 6.4088. Min Act: -0.1700
Data Index: 4591961 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19