Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 500 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5158. Min Range: -9.5158
Max Act: 9.5158. Min Act: -0.1700
Data Index: 4451556 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5158. Min Range: -9.5158
Max Act: 9.0158. Min Act: -0.1700
Data Index: 361209 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.7033. Min Act: -0.1700
Data Index: 7044675 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.6408. Min Act: -0.1700
Data Index: 2591247 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.6408. Min Act: -0.1700
Data Index: 4451560 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.6408. Min Act: -0.1700
Data Index: 4659921 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.5158. Min Act: -0.1700
Data Index: 7026300 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.5783. Min Act: -0.1700
Data Index: 3106199 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.5783. Min Act: -0.1700
Data Index: 1066292 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.5783. Min Act: -0.1700
Data Index: 635115 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.5783. Min Act: -0.1700
Data Index: 6453282 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.5158. Min Act: -0.1700
Data Index: 5822764 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.4533. Min Act: -0.1700
Data Index: 6801445 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.4533. Min Act: -0.1700
Data Index: 3792943 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.4533. Min Act: -0.1700
Data Index: 1046196 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.4533. Min Act: -0.1700
Data Index: 4747399 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.3283. Min Act: -0.1700
Data Index: 7720816 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.3283. Min Act: -0.1700
Data Index: 2277625 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.3908. Min Act: -0.1700
Data Index: 639237 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5158. Min Range: -9.5158
Max Act: 8.3283. Min Act: -0.1700
Data Index: 2500264 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19