Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2981 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2518. Min Range: -6.2518
Max Act: 6.2518. Min Act: -0.1700
Data Index: 121191 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.8768. Min Act: -0.1700
Data Index: 5264338 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.8143. Min Act: -0.1700
Data Index: 7968404 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.7518. Min Act: -0.1700
Data Index: 4075085 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.6893. Min Act: -0.1700
Data Index: 3321134 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.6268. Min Act: -0.1700
Data Index: 6571860 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.6581. Min Act: -0.1700
Data Index: 2603726 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.6581. Min Act: -0.1700
Data Index: 1401958 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.5643. Min Act: -0.1700
Data Index: 3524278 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.6268. Min Act: -0.1700
Data Index: 6251275 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.5643. Min Act: -0.1700
Data Index: 7535544 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.5018. Min Act: -0.1700
Data Index: 8767214 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.5018. Min Act: -0.1700
Data Index: 3357691 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.5331. Min Act: -0.1700
Data Index: 7836669 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.5018. Min Act: -0.1700
Data Index: 4160384 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.5018. Min Act: -0.1700
Data Index: 6026298 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.5018. Min Act: -0.1700
Data Index: 432400 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.4706. Min Act: -0.1700
Data Index: 3963970 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.5018. Min Act: -0.1700
Data Index: 7613419 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2518. Min Range: -6.2518
Max Act: 5.4706. Min Act: -0.1700
Data Index: 2351453 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19