Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5459 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.4567. Min Act: -0.1700
Data Index: 692834 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.2692. Min Act: -0.1700
Data Index: 3235412 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.2380. Min Act: -0.1700
Data Index: 6810772 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.2380. Min Act: -0.1700
Data Index: 934782 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.2380. Min Act: -0.1700
Data Index: 553717 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.2380. Min Act: -0.1700
Data Index: 3878463 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.1755. Min Act: -0.1700
Data Index: 3965963 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.1755. Min Act: -0.1700
Data Index: 480972 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.1755. Min Act: -0.1700
Data Index: 5983437 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.1442. Min Act: -0.1700
Data Index: 6049140 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.1755. Min Act: -0.1700
Data Index: 3412567 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.1442. Min Act: -0.1700
Data Index: 6726951 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.1130. Min Act: -0.1700
Data Index: 3416149 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0817. Min Act: -0.1700
Data Index: 4203896 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0817. Min Act: -0.1700
Data Index: 4099100 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0817. Min Act: -0.1700
Data Index: 8092922 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0505. Min Act: -0.1700
Data Index: 4951352 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0505. Min Act: -0.1700
Data Index: 2085517 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0505. Min Act: -0.1700
Data Index: 581714 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4567. Min Range: -5.4567
Max Act: 5.0192. Min Act: -0.1700
Data Index: 4850528 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19