Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4064 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.4609. Min Act: -0.1700
Data Index: 7274303 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.3359. Min Act: -0.1700
Data Index: 5231334 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.3047. Min Act: -0.1700
Data Index: 1724518 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.2734. Min Act: -0.1700
Data Index: 7660003 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.1797. Min Act: -0.1700
Data Index: 3894008 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.1484. Min Act: -0.1700
Data Index: 4629051 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.1484. Min Act: -0.1700
Data Index: 7445079 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.1484. Min Act: -0.1700
Data Index: 3545329 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.1172. Min Act: -0.1700
Data Index: 3544209 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.1172. Min Act: -0.1700
Data Index: 4117112 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.0859. Min Act: -0.1700
Data Index: 5313443 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.0547. Min Act: -0.1700
Data Index: 2943439 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.0547. Min Act: -0.1700
Data Index: 4430458 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.0234. Min Act: -0.1700
Data Index: 374659 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.0234. Min Act: -0.1700
Data Index: 609122 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.0234. Min Act: -0.1700
Data Index: 7468890 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4609. Min Range: -6.4609
Max Act: 5.9922. Min Act: -0.1700
Data Index: 2316022 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4609. Min Range: -6.4609
Max Act: 5.9922. Min Act: -0.1700
Data Index: 3196923 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4609. Min Range: -6.4609
Max Act: 6.0234. Min Act: -0.1700
Data Index: 6442613 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4609. Min Range: -6.4609
Max Act: 5.9922. Min Act: -0.1700
Data Index: 4330326 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19