Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2276 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.8374. Min Act: -0.1700
Data Index: 1432839 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.7124. Min Act: -0.1700
Data Index: 2363267 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.6499. Min Act: -0.1700
Data Index: 371566 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.6499. Min Act: -0.1700
Data Index: 7769722 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.5874. Min Act: -0.1700
Data Index: 6847041 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.5874. Min Act: -0.1700
Data Index: 5160444 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.5874. Min Act: -0.1700
Data Index: 4742017 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.5249. Min Act: -0.1700
Data Index: 2689004 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.5249. Min Act: -0.1700
Data Index: 8486839 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.3999. Min Act: -0.1700
Data Index: 3707337 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.3999. Min Act: -0.1700
Data Index: 3658213 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.4624. Min Act: -0.1700
Data Index: 5505780 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.3999. Min Act: -0.1700
Data Index: 5970183 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.3999. Min Act: -0.1700
Data Index: 8440760 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.3999. Min Act: -0.1700
Data Index: 3598259 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.3999. Min Act: -0.1700
Data Index: 4933105 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.3374. Min Act: -0.1700
Data Index: 5607213 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.3061. Min Act: -0.1700
Data Index: 4063945 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.2749. Min Act: -0.1700
Data Index: 944324 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8374. Min Range: -8.8374
Max Act: 8.3061. Min Act: -0.1700
Data Index: 6226978 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #19