Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1670 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5862. Min Range: -5.5862
Max Act: 5.5862. Min Act: -0.1700
Data Index: 4433895 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5862. Min Range: -5.5862
Max Act: 5.2112. Min Act: -0.1652
Data Index: 185410 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5862. Min Range: -5.5862
Max Act: 5.1487. Min Act: -0.1700
Data Index: 2825713 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5862. Min Range: -5.5862
Max Act: 5.0862. Min Act: -0.1700
Data Index: 3330943 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5862. Min Range: -5.5862
Max Act: 5.0549. Min Act: -0.1700
Data Index: 871160 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5862. Min Range: -5.5862
Max Act: 5.0237. Min Act: -0.1700
Data Index: 5191789 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.9924. Min Act: -0.1700
Data Index: 185412 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.9924. Min Act: -0.1700
Data Index: 175778 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.9299. Min Act: -0.1700
Data Index: 7752249 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.9299. Min Act: -0.1700
Data Index: 185411 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.8987. Min Act: -0.1700
Data Index: 850939 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.8987. Min Act: -0.1700
Data Index: 7126823 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.8987. Min Act: -0.1700
Data Index: 1315102 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.8987. Min Act: -0.1700
Data Index: 2403206 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.8674. Min Act: -0.1700
Data Index: 8483278 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.8674. Min Act: -0.1700
Data Index: 8166632 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.8362. Min Act: -0.1700
Data Index: 7378852 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.8674. Min Act: -0.1700
Data Index: 6301213 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.8049. Min Act: -0.1700
Data Index: 5428499 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5862. Min Range: -5.5862
Max Act: 4.7737. Min Act: -0.1700
Data Index: 6968985 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19