Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4154 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.9052. Min Act: -0.1700
Data Index: 4580466 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.7489. Min Act: -0.1700
Data Index: 6357036 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.6864. Min Act: -0.1700
Data Index: 3832402 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.6552. Min Act: -0.1700
Data Index: 684575 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.4989. Min Act: -0.1700
Data Index: 677902 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.4364. Min Act: -0.1700
Data Index: 4149456 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.4052. Min Act: -0.1700
Data Index: 1094617 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.4364. Min Act: -0.1700
Data Index: 7923427 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.2177. Min Act: -0.1700
Data Index: 7959267 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.1552. Min Act: -0.1700
Data Index: 6895480 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.1239. Min Act: -0.1700
Data Index: 4084011 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.1239. Min Act: -0.1700
Data Index: 8603320 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.1239. Min Act: -0.1700
Data Index: 4978959 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.1239. Min Act: -0.1700
Data Index: 1867640 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.0927. Min Act: -0.1700
Data Index: 3589226 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.0302. Min Act: -0.1700
Data Index: 862445 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.0302. Min Act: -0.1700
Data Index: 886550 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.0302. Min Act: -0.1700
Data Index: 8018931 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9052. Min Range: -7.9052
Max Act: 7.0302. Min Act: -0.1700
Data Index: 5692291 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9052. Min Range: -7.9052
Max Act: 6.9989. Min Act: -0.1700
Data Index: 8536106 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19