Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3640 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.9400. Min Act: -0.1700
Data Index: 1296703 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.8775. Min Act: -0.1700
Data Index: 8088088 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.8150. Min Act: -0.1700
Data Index: 6414697 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.5025. Min Act: -0.1700
Data Index: 8682375 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.5025. Min Act: -0.1700
Data Index: 2304512 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.5025. Min Act: -0.1700
Data Index: 6115755 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.4400. Min Act: -0.1700
Data Index: 3597059 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.4400. Min Act: -0.1700
Data Index: 2205955 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.5025. Min Act: -0.1700
Data Index: 2442152 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.4400. Min Act: -0.1700
Data Index: 1925486 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.4087. Min Act: -0.1700
Data Index: 1984073 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.3775. Min Act: -0.1700
Data Index: 3683166 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.3775. Min Act: -0.1700
Data Index: 268708 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.3462. Min Act: -0.1700
Data Index: 1928365 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.3150. Min Act: -0.1700
Data Index: 2260248 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.2525. Min Act: -0.1700
Data Index: 1066085 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.2212. Min Act: -0.1700
Data Index: 7863956 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.1900. Min Act: -0.1700
Data Index: 1846309 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.1587. Min Act: -0.1700
Data Index: 7346032 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9400. Min Range: -7.9400
Max Act: 7.1587. Min Act: -0.1700
Data Index: 604246 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19