Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3380 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.9865. Min Act: -0.1700
Data Index: 4218382 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.9074. Min Act: -0.1700
Data Index: 2236145 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.9074. Min Act: -0.1700
Data Index: 2080835 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.8756. Min Act: -0.1700
Data Index: 5139876 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.8121. Min Act: -0.1700
Data Index: 2694891 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7961. Min Act: -0.1700
Data Index: 720095 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7802. Min Act: -0.1700
Data Index: 1684738 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7802. Min Act: -0.1700
Data Index: 5165879 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7643. Min Act: -0.1700
Data Index: 8436074 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7643. Min Act: -0.1700
Data Index: 5165880 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7643. Min Act: -0.1700
Data Index: 8362007 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7483. Min Act: -0.1700
Data Index: 167870 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7323. Min Act: -0.1700
Data Index: 7744384 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7643. Min Act: -0.1700
Data Index: 567204 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7323. Min Act: -0.1700
Data Index: 2546334 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7323. Min Act: -0.1700
Data Index: 1684740 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7483. Min Act: -0.1700
Data Index: 511691 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7163. Min Act: -0.1700
Data Index: 781842 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7323. Min Act: -0.1700
Data Index: 1929261 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9865. Min Range: -2.9865
Max Act: 2.7004. Min Act: -0.1700
Data Index: 5226063 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19