Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5580 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.5578. Min Act: -0.1700
Data Index: 7926049 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.5266. Min Act: -0.1700
Data Index: 7858764 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.4016. Min Act: -0.1700
Data Index: 3353165 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.4328. Min Act: -0.1700
Data Index: 80486 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.4016. Min Act: -0.1700
Data Index: 4079966 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.3703. Min Act: -0.1700
Data Index: 2871693 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.3703. Min Act: -0.1700
Data Index: 5060778 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.3391. Min Act: -0.1700
Data Index: 3107229 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.3078. Min Act: -0.1700
Data Index: 8313520 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.3078. Min Act: -0.1700
Data Index: 2081655 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.2766. Min Act: -0.1700
Data Index: 4515741 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.2766. Min Act: -0.1700
Data Index: 8547052 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.2766. Min Act: -0.1700
Data Index: 3163649 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.2453. Min Act: -0.1700
Data Index: 5805381 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.2453. Min Act: -0.1700
Data Index: 477680 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.2141. Min Act: -0.1700
Data Index: 2058071 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.2141. Min Act: -0.1700
Data Index: 5531330 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.2453. Min Act: -0.1700
Data Index: 5309575 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.2141. Min Act: -0.1700
Data Index: 3899614 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5578. Min Range: -5.5578
Max Act: 5.2141. Min Act: -0.1700
Data Index: 8497640 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19