Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 399 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.4619. Min Act: -0.1700
Data Index: 8511913 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.2744. Min Act: -0.1700
Data Index: 612702 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.2431. Min Act: -0.1700
Data Index: 672005 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.2119. Min Act: -0.1700
Data Index: 8630125 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.1806. Min Act: -0.1700
Data Index: 4909442 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.1494. Min Act: -0.1700
Data Index: 2981143 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.1806. Min Act: -0.1700
Data Index: 2223643 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.1181. Min Act: -0.1700
Data Index: 4141272 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.1181. Min Act: -0.1700
Data Index: 7462149 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.0869. Min Act: -0.1700
Data Index: 5276778 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.0556. Min Act: -0.1700
Data Index: 3219909 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.0556. Min Act: -0.1700
Data Index: 1632710 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.0244. Min Act: -0.1700
Data Index: 2723657 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.0244. Min Act: -0.1700
Data Index: 460710 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.0244. Min Act: -0.1700
Data Index: 2306786 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.0244. Min Act: -0.1700
Data Index: 6888992 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4619. Min Range: -6.4619
Max Act: 6.0244. Min Act: -0.1700
Data Index: 1939509 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4619. Min Range: -6.4619
Max Act: 5.9931. Min Act: -0.1700
Data Index: 637146 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4619. Min Range: -6.4619
Max Act: 5.9931. Min Act: -0.1700
Data Index: 4326521 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4619. Min Range: -6.4619
Max Act: 5.9931. Min Act: -0.1700
Data Index: 5725892 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19