Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3097 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1096. Min Range: -6.1096
Max Act: 6.1096. Min Act: -0.1700
Data Index: 7481838 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1096. Min Range: -6.1096
Max Act: 6.0471. Min Act: -0.1700
Data Index: 2539294 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1096. Min Range: -6.1096
Max Act: 6.0158. Min Act: -0.1700
Data Index: 2618873 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9846. Min Act: -0.1700
Data Index: 3092040 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9533. Min Act: -0.1700
Data Index: 5550221 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9846. Min Act: -0.1700
Data Index: 7366120 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9846. Min Act: -0.1700
Data Index: 8343491 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9533. Min Act: -0.1700
Data Index: 7201458 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9533. Min Act: -0.1700
Data Index: 4213972 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9533. Min Act: -0.1700
Data Index: 4421434 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9533. Min Act: -0.1700
Data Index: 7346892 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9533. Min Act: -0.1700
Data Index: 730810 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9221. Min Act: -0.1700
Data Index: 6766984 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9221. Min Act: -0.1700
Data Index: 2599620 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9221. Min Act: -0.1700
Data Index: 5149288 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9221. Min Act: -0.1700
Data Index: 5877806 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9221. Min Act: -0.1700
Data Index: 756103 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9221. Min Act: -0.1700
Data Index: 4444707 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.9221. Min Act: -0.1700
Data Index: 3483520 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1096. Min Range: -6.1096
Max Act: 5.8908. Min Act: -0.1700
Data Index: 6218017 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19