Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0365. Min Range: -1.0365
Max Act: 1.0365. Min Act: -0.1696
Data Index: 7699166 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0365. Min Range: -1.0365
Max Act: 1.0061. Min Act: -0.1700
Data Index: 6537709 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0365. Min Range: -1.0365
Max Act: 1.0104. Min Act: -0.1700
Data Index: 6995344 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.9931. Min Act: -0.1700
Data Index: 4644775 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.9369. Min Act: -0.1699
Data Index: 3809828 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.9412. Min Act: -0.1700
Data Index: 3974495 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.9240. Min Act: -0.1700
Data Index: 1166289 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.9240. Min Act: -0.1700
Data Index: 4108310 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.9026. Min Act: -0.1700
Data Index: 1556547 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.9154. Min Act: -0.1700
Data Index: 6559087 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.9069. Min Act: -0.1700
Data Index: 3484537 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.8770. Min Act: -0.1700
Data Index: 2375847 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.8983. Min Act: -0.1700
Data Index: 6307315 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.8727. Min Act: -0.1699
Data Index: 3974497 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.8770. Min Act: -0.1700
Data Index: 5701687 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.8685. Min Act: -0.1690
Data Index: 1668009 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.8685. Min Act: -0.1700
Data Index: 7063242 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.8642. Min Act: -0.1698
Data Index: 7002410 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.8600. Min Act: -0.1700
Data Index: 5251310 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0365. Min Range: -1.0365
Max Act: 0.8303. Min Act: -0.1700
Data Index: 5991545 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #19