Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0999. Min Range: -9.0999
Max Act: 9.0999. Min Act: -0.1700
Data Index: 1593785 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0999. Min Range: -9.0999
Max Act: 9.0999. Min Act: -0.1700
Data Index: 4417250 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0999. Min Range: -9.0999
Max Act: 9.0999. Min Act: -0.1700
Data Index: 6409351 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.9749. Min Act: -0.1700
Data Index: 1593784 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.6624. Min Act: -0.1700
Data Index: 2101755 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.7249. Min Act: -0.1700
Data Index: 132642 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.6624. Min Act: -0.1700
Data Index: 1349447 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.5999. Min Act: -0.1700
Data Index: 3005227 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.6624. Min Act: -0.1700
Data Index: 5098797 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.5999. Min Act: -0.1700
Data Index: 4161340 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.4749. Min Act: -0.1700
Data Index: 2036130 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.4124. Min Act: -0.1700
Data Index: 5518398 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.2874. Min Act: -0.1700
Data Index: 5045917 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.2874. Min Act: -0.1700
Data Index: 6503854 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.2874. Min Act: -0.1700
Data Index: 7554509 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.2249. Min Act: -0.1700
Data Index: 8008100 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.2249. Min Act: -0.1700
Data Index: 5835891 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.0999. Min Act: -0.1700
Data Index: 2548085 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.1624. Min Act: -0.1700
Data Index: 3364004 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0999. Min Range: -9.0999
Max Act: 8.1624. Min Act: -0.1700
Data Index: 4161341 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #19