Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4496 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0449. Min Range: -6.0449
Max Act: 6.0449. Min Act: -0.1700
Data Index: 7154263 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.9199. Min Act: -0.1700
Data Index: 8573401 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.8886. Min Act: -0.1700
Data Index: 4185854 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.8886. Min Act: -0.1700
Data Index: 3580190 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7949. Min Act: -0.1700
Data Index: 7306956 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7636. Min Act: -0.1700
Data Index: 3435517 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7949. Min Act: -0.1700
Data Index: 7812319 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7324. Min Act: -0.1700
Data Index: 7782881 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7324. Min Act: -0.1700
Data Index: 4332128 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7324. Min Act: -0.1700
Data Index: 1589061 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7324. Min Act: -0.1700
Data Index: 8374149 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7011. Min Act: -0.1700
Data Index: 675828 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7324. Min Act: -0.1700
Data Index: 6775234 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7011. Min Act: -0.1700
Data Index: 2134461 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7011. Min Act: -0.1700
Data Index: 4185852 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.6699. Min Act: -0.1700
Data Index: 8066622 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.6699. Min Act: -0.1700
Data Index: 4962415 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.6699. Min Act: -0.1700
Data Index: 2863136 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.7011. Min Act: -0.1700
Data Index: 5155302 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0449. Min Range: -6.0449
Max Act: 5.6386. Min Act: -0.1700
Data Index: 4381454 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19