Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5402 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6540. Min Range: -5.6540
Max Act: 5.6540. Min Act: -0.1700
Data Index: 8391235 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6540. Min Range: -5.6540
Max Act: 5.3415. Min Act: -0.1700
Data Index: 5358779 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6540. Min Range: -5.6540
Max Act: 5.1852. Min Act: -0.1700
Data Index: 1241025 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6540. Min Range: -5.6540
Max Act: 5.1852. Min Act: -0.1700
Data Index: 6506617 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6540. Min Range: -5.6540
Max Act: 5.1540. Min Act: -0.1700
Data Index: 18259 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6540. Min Range: -5.6540
Max Act: 5.1540. Min Act: -0.1700
Data Index: 8318556 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6540. Min Range: -5.6540
Max Act: 5.1227. Min Act: -0.1700
Data Index: 1298836 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6540. Min Range: -5.6540
Max Act: 5.0915. Min Act: -0.1700
Data Index: 5598928 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6540. Min Range: -5.6540
Max Act: 5.0915. Min Act: -0.1700
Data Index: 2977042 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.9977. Min Act: -0.1700
Data Index: 3759694 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.9977. Min Act: -0.1700
Data Index: 8652989 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.9665. Min Act: -0.1700
Data Index: 6920421 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.9665. Min Act: -0.1700
Data Index: 107510 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.9665. Min Act: -0.1700
Data Index: 313821 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.9352. Min Act: -0.1700
Data Index: 4707232 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.9665. Min Act: -0.1700
Data Index: 3161574 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.9040. Min Act: -0.1700
Data Index: 777346 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.9040. Min Act: -0.1700
Data Index: 7476637 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.9040. Min Act: -0.1700
Data Index: 2560090 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6540. Min Range: -5.6540
Max Act: 4.8727. Min Act: -0.1700
Data Index: 6427703 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19