Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5320 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0090. Min Range: -5.0090
Max Act: 5.0090. Min Act: -0.1700
Data Index: 4474724 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.9778. Min Act: -0.1700
Data Index: 5438530 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.9465. Min Act: -0.1700
Data Index: 4567952 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.9465. Min Act: -0.1700
Data Index: 8497132 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.8528. Min Act: -0.1700
Data Index: 4879474 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.8528. Min Act: -0.1700
Data Index: 5159698 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.8215. Min Act: -0.1700
Data Index: 650874 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.8215. Min Act: -0.1700
Data Index: 4622353 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7903. Min Act: -0.1700
Data Index: 2656580 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.8215. Min Act: -0.1700
Data Index: 7623281 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7903. Min Act: -0.1700
Data Index: 3168224 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7590. Min Act: -0.1700
Data Index: 7885456 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7903. Min Act: -0.1700
Data Index: 4656357 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7903. Min Act: -0.1700
Data Index: 8614258 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7590. Min Act: -0.1700
Data Index: 4122516 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7590. Min Act: -0.1700
Data Index: 8480476 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7590. Min Act: -0.1700
Data Index: 237604 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7590. Min Act: -0.1700
Data Index: 1594676 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7278. Min Act: -0.1700
Data Index: 716020 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0090. Min Range: -5.0090
Max Act: 4.7278. Min Act: -0.1700
Data Index: 3408289 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19