Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.5566. Min Act: -0.1700
Data Index: 5991323 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.2753. Min Act: -0.1700
Data Index: 3646262 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.2753. Min Act: -0.1700
Data Index: 3828859 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.2128. Min Act: -0.1700
Data Index: 1237584 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.1503. Min Act: -0.1700
Data Index: 4111510 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.1816. Min Act: -0.1700
Data Index: 3880263 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.1503. Min Act: -0.1700
Data Index: 3524271 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.1191. Min Act: -0.1700
Data Index: 2630386 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.0878. Min Act: -0.1700
Data Index: 1394202 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.1191. Min Act: -0.1700
Data Index: 1310070 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.0878. Min Act: -0.1700
Data Index: 4826594 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.0878. Min Act: -0.1700
Data Index: 1070290 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.0253. Min Act: -0.1700
Data Index: 6833980 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.0566. Min Act: -0.1700
Data Index: 6606074 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.0566. Min Act: -0.1700
Data Index: 61927 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.0253. Min Act: -0.1700
Data Index: 450727 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5566. Min Range: -4.5566
Max Act: 4.0253. Min Act: -0.1700
Data Index: 4325814 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5566. Min Range: -4.5566
Max Act: 3.9940. Min Act: -0.1700
Data Index: 4933434 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5566. Min Range: -4.5566
Max Act: 3.9940. Min Act: -0.1700
Data Index: 7113296 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5566. Min Range: -4.5566
Max Act: 3.9940. Min Act: -0.1700
Data Index: 6732538 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19