Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3589 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 15.4474. Min Range: -15.4474
Max Act: 15.4474. Min Act: -0.1700
Data Index: 4479372 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.4474. Min Act: -0.1700
Data Index: 55256 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.3849. Min Act: -0.1700
Data Index: 6079595 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.4474. Min Act: -0.1700
Data Index: 2281146 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.3849. Min Act: -0.1700
Data Index: 5611077 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.3224. Min Act: -0.1700
Data Index: 5406827 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.3224. Min Act: -0.1700
Data Index: 5243935 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.2599. Min Act: -0.1700
Data Index: 385306 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.1974. Min Act: -0.1700
Data Index: 360746 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.1974. Min Act: -0.1700
Data Index: 5654264 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.1349. Min Act: -0.1700
Data Index: 2405968 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.1349. Min Act: -0.1700
Data Index: 2442750 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.0724. Min Act: -0.1700
Data Index: 7100775 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.0724. Min Act: -0.1700
Data Index: 1201644 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 15.4474. Min Range: -15.4474
Max Act: 14.0724. Min Act: -0.1700
Data Index: 7876056 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 15.4474. Min Range: -15.4474
Max Act: 13.9474. Min Act: -0.1700
Data Index: 4463475 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 15.4474. Min Range: -15.4474
Max Act: 13.9474. Min Act: -0.1700
Data Index: 8750864 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 15.4474. Min Range: -15.4474
Max Act: 13.9474. Min Act: -0.1700
Data Index: 7804361 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 15.4474. Min Range: -15.4474
Max Act: 13.9474. Min Act: -0.1700
Data Index: 4741710 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 15.4474. Min Range: -15.4474
Max Act: 13.8849. Min Act: -0.1700
Data Index: 4491101 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19