Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2565 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2578. Min Range: -7.2578
Max Act: 7.2578. Min Act: -0.1700
Data Index: 8599159 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2578. Min Range: -7.2578
Max Act: 7.1953. Min Act: -0.1700
Data Index: 706018 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2578. Min Range: -7.2578
Max Act: 7.1016. Min Act: -0.1700
Data Index: 500178 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2578. Min Range: -7.2578
Max Act: 7.1328. Min Act: -0.1700
Data Index: 1082062 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2578. Min Range: -7.2578
Max Act: 7.0391. Min Act: -0.1700
Data Index: 1938496 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2578. Min Range: -7.2578
Max Act: 7.0703. Min Act: -0.1700
Data Index: 2913807 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2578. Min Range: -7.2578
Max Act: 7.0078. Min Act: -0.1700
Data Index: 2688346 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2578. Min Range: -7.2578
Max Act: 7.0078. Min Act: -0.1700
Data Index: 850613 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.9766. Min Act: -0.1700
Data Index: 1082061 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.9453. Min Act: -0.1700
Data Index: 1916816 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.9453. Min Act: -0.1700
Data Index: 6362116 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.9453. Min Act: -0.1700
Data Index: 4954059 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.9141. Min Act: -0.1700
Data Index: 4505105 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.9453. Min Act: -0.1700
Data Index: 5670114 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.9141. Min Act: -0.1700
Data Index: 2221326 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.9453. Min Act: -0.1700
Data Index: 3790201 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.8828. Min Act: -0.1700
Data Index: 4512488 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.8516. Min Act: -0.1700
Data Index: 8461620 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.8203. Min Act: -0.1700
Data Index: 267045 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2578. Min Range: -7.2578
Max Act: 6.8828. Min Act: -0.1700
Data Index: 2756688 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #19