Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1823 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.7418. Min Act: -0.1700
Data Index: 346069 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.7418. Min Act: -0.1700
Data Index: 753428 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.7105. Min Act: -0.1700
Data Index: 5633280 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.6793. Min Act: -0.1700
Data Index: 4746761 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.6793. Min Act: -0.1700
Data Index: 5332578 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.6480. Min Act: -0.1700
Data Index: 8016598 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.6480. Min Act: -0.1700
Data Index: 7442482 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.6480. Min Act: -0.1700
Data Index: 3090946 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.6480. Min Act: -0.1700
Data Index: 624751 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.6168. Min Act: -0.1700
Data Index: 1464000 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.5855. Min Act: -0.1700
Data Index: 7123168 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.5855. Min Act: -0.1700
Data Index: 2162064 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.5543. Min Act: -0.1700
Data Index: 2589734 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.5855. Min Act: -0.1700
Data Index: 6949058 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.5855. Min Act: -0.1700
Data Index: 8270674 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.6168. Min Act: -0.1700
Data Index: 8169362 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.5543. Min Act: -0.1700
Data Index: 6347790 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.5855. Min Act: -0.1700
Data Index: 7703563 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.5543. Min Act: -0.1700
Data Index: 7318170 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7418. Min Range: -4.7418
Max Act: 4.5543. Min Act: -0.1700
Data Index: 7423844 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19