Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3118 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.6696. Min Act: -0.1700
Data Index: 1072382 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.6384. Min Act: -0.1700
Data Index: 3894763 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.6071. Min Act: -0.1700
Data Index: 465875 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.5759. Min Act: -0.1700
Data Index: 1860795 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.5759. Min Act: -0.1700
Data Index: 8241572 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.5446. Min Act: -0.1700
Data Index: 8683000 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.4821. Min Act: -0.1700
Data Index: 1261834 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.4821. Min Act: -0.1700
Data Index: 1255859 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.4509. Min Act: -0.1700
Data Index: 7979526 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.4509. Min Act: -0.1700
Data Index: 7609372 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.3884. Min Act: -0.1700
Data Index: 1261835 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.3884. Min Act: -0.1700
Data Index: 4194035 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.3884. Min Act: -0.1700
Data Index: 2711833 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.3571. Min Act: -0.1700
Data Index: 3221367 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.3571. Min Act: -0.1700
Data Index: 352991 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.3571. Min Act: -0.1700
Data Index: 806515 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.3571. Min Act: -0.1700
Data Index: 5746664 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.3259. Min Act: -0.1700
Data Index: 387207 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.2946. Min Act: -0.1700
Data Index: 2062133 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6696. Min Range: -5.6696
Max Act: 5.3259. Min Act: -0.1700
Data Index: 4063999 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19