Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3808 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.7488. Min Act: -0.1700
Data Index: 559303 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.7175. Min Act: -0.1700
Data Index: 4274568 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.6550. Min Act: -0.1700
Data Index: 4113777 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.6550. Min Act: -0.1700
Data Index: 3247812 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.7175. Min Act: -0.1700
Data Index: 2087227 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.6863. Min Act: -0.1700
Data Index: 637113 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.6238. Min Act: -0.1700
Data Index: 2548806 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.6550. Min Act: -0.1700
Data Index: 8783376 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.6550. Min Act: -0.1700
Data Index: 4402904 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.6550. Min Act: -0.1700
Data Index: 8815813 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.6238. Min Act: -0.1700
Data Index: 8199652 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.6238. Min Act: -0.1700
Data Index: 3570358 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.5925. Min Act: -0.1700
Data Index: 5211328 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.5613. Min Act: -0.1700
Data Index: 5681537 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.5925. Min Act: -0.1700
Data Index: 4922703 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.5925. Min Act: -0.1700
Data Index: 3284291 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.5925. Min Act: -0.1700
Data Index: 7109713 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.5613. Min Act: -0.1700
Data Index: 5977864 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.5613. Min Act: -0.1700
Data Index: 1023046 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7488. Min Range: -4.7488
Max Act: 4.5613. Min Act: -0.1700
Data Index: 191056 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19