Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3302 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0421. Min Range: -7.0421
Max Act: 7.0421. Min Act: -0.1700
Data Index: 7339239 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0421. Min Range: -7.0421
Max Act: 7.0421. Min Act: -0.1700
Data Index: 3920126 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.9796. Min Act: -0.1700
Data Index: 4822337 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.9796. Min Act: -0.1700
Data Index: 1661957 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.9483. Min Act: -0.1700
Data Index: 6673818 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.8858. Min Act: -0.1700
Data Index: 2224347 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.8858. Min Act: -0.1700
Data Index: 6164052 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.8546. Min Act: -0.1700
Data Index: 8088581 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.8546. Min Act: -0.1700
Data Index: 2351943 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.8546. Min Act: -0.1700
Data Index: 6975379 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.8233. Min Act: -0.1700
Data Index: 5361474 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.7921. Min Act: -0.1700
Data Index: 3418970 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.7921. Min Act: -0.1700
Data Index: 7522023 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.7921. Min Act: -0.1700
Data Index: 857195 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.8233. Min Act: -0.1700
Data Index: 7047627 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.7921. Min Act: -0.1700
Data Index: 5471055 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.7921. Min Act: -0.1700
Data Index: 1197304 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.6983. Min Act: -0.1700
Data Index: 7181350 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.6671. Min Act: -0.1700
Data Index: 2312502 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0421. Min Range: -7.0421
Max Act: 6.6358. Min Act: -0.1700
Data Index: 5491642 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19