Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5813 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0107. Min Range: -9.0107
Max Act: 9.0107. Min Act: -0.1700
Data Index: 2582896 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.8857. Min Act: -0.1700
Data Index: 42245 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.8857. Min Act: -0.1700
Data Index: 1995248 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.8232. Min Act: -0.1700
Data Index: 7116818 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.7607. Min Act: -0.1700
Data Index: 3090390 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.7607. Min Act: -0.1700
Data Index: 4744291 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.7607. Min Act: -0.1700
Data Index: 6426836 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.7607. Min Act: -0.1700
Data Index: 5512790 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.6982. Min Act: -0.1700
Data Index: 787187 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.6982. Min Act: -0.1700
Data Index: 1828841 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.6982. Min Act: -0.1700
Data Index: 8240291 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.6982. Min Act: -0.1700
Data Index: 3904545 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.6357. Min Act: -0.1700
Data Index: 1356533 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.6982. Min Act: -0.1700
Data Index: 6768591 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.6357. Min Act: -0.1700
Data Index: 3569312 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.6357. Min Act: -0.1700
Data Index: 5287659 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.5732. Min Act: -0.1700
Data Index: 5287661 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.5107. Min Act: -0.1700
Data Index: 1797 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.5107. Min Act: -0.1700
Data Index: 590319 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0107. Min Range: -9.0107
Max Act: 8.5107. Min Act: -0.1700
Data Index: 278399 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19