Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1423 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.8964. Min Act: -0.1700
Data Index: 4879883 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.6152. Min Act: -0.1700
Data Index: 3210966 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.5839. Min Act: -0.1700
Data Index: 3134268 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.5214. Min Act: -0.1700
Data Index: 2962165 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.4277. Min Act: -0.1700
Data Index: 8215029 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.4277. Min Act: -0.1700
Data Index: 4868103 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.4277. Min Act: -0.1700
Data Index: 7463187 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.3652. Min Act: -0.1700
Data Index: 1011833 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.3027. Min Act: -0.1700
Data Index: 7714900 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.3027. Min Act: -0.1700
Data Index: 3278984 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.2089. Min Act: -0.1700
Data Index: 5564164 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.1777. Min Act: -0.1700
Data Index: 7802807 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.1777. Min Act: -0.1700
Data Index: 3417883 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.1777. Min Act: -0.1700
Data Index: 5955711 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.1777. Min Act: -0.1700
Data Index: 3889135 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.1777. Min Act: -0.1700
Data Index: 185723 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.1777. Min Act: -0.1700
Data Index: 5128056 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.1464. Min Act: -0.1700
Data Index: 3473433 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.1464. Min Act: -0.1700
Data Index: 142801 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8964. Min Range: -6.8964
Max Act: 6.1152. Min Act: -0.1700
Data Index: 443482 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19