Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1878 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.6540. Min Act: -0.1700
Data Index: 3196819 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.6228. Min Act: -0.1700
Data Index: 2709214 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.6228. Min Act: -0.1700
Data Index: 2642534 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.6228. Min Act: -0.1700
Data Index: 5207059 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.5603. Min Act: -0.1700
Data Index: 4573470 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4977. Min Act: -0.1700
Data Index: 1997074 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4977. Min Act: -0.1700
Data Index: 1635790 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4977. Min Act: -0.1700
Data Index: 4005745 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4977. Min Act: -0.1700
Data Index: 2667447 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4977. Min Act: -0.1700
Data Index: 6917302 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4352. Min Act: -0.1700
Data Index: 2722968 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4665. Min Act: -0.1700
Data Index: 239204 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4040. Min Act: -0.1700
Data Index: 2597689 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4352. Min Act: -0.1700
Data Index: 485108 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4040. Min Act: -0.1700
Data Index: 5027909 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4040. Min Act: -0.1700
Data Index: 5262454 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4040. Min Act: -0.1700
Data Index: 5710501 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4040. Min Act: -0.1700
Data Index: 5771784 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4040. Min Act: -0.1700
Data Index: 1220376 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6540. Min Range: -4.6540
Max Act: 4.4040. Min Act: -0.1700
Data Index: 2104470 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #19