Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 857 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0990. Min Range: -3.0990
Max Act: 3.0990. Min Act: -0.1700
Data Index: 3791051 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0990. Min Range: -3.0990
Max Act: 3.0990. Min Act: -0.1700
Data Index: 4920254 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.9885. Min Act: -0.1700
Data Index: 191734 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0990. Min Range: -3.0990
Max Act: 3.0043. Min Act: -0.1700
Data Index: 5028836 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.9727. Min Act: -0.1700
Data Index: 2704869 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.9569. Min Act: -0.1700
Data Index: 2579385 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.9411. Min Act: -0.1700
Data Index: 2921379 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.9094. Min Act: -0.1700
Data Index: 6829583 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.8935. Min Act: -0.1700
Data Index: 3791052 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.8777. Min Act: -0.1700
Data Index: 3791053 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.9094. Min Act: -0.1700
Data Index: 3334633 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.8777. Min Act: -0.1700
Data Index: 2348877 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.8618. Min Act: -0.1700
Data Index: 6212785 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.8618. Min Act: -0.1700
Data Index: 6651030 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.8459. Min Act: -0.1700
Data Index: 2896114 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.8459. Min Act: -0.1700
Data Index: 1295808 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.8300. Min Act: -0.1700
Data Index: 5277511 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.7982. Min Act: -0.1700
Data Index: 2502616 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.7982. Min Act: -0.1700
Data Index: 4854390 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0990. Min Range: -3.0990
Max Act: 2.7982. Min Act: -0.1700
Data Index: 5767919 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19