Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4077 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2090. Min Range: -6.2090
Max Act: 6.2090. Min Act: -0.1700
Data Index: 5351928 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2090. Min Range: -6.2090
Max Act: 6.2090. Min Act: -0.1700
Data Index: 6046983 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2090. Min Range: -6.2090
Max Act: 6.1465. Min Act: -0.1700
Data Index: 7660363 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2090. Min Range: -6.2090
Max Act: 6.1153. Min Act: -0.1700
Data Index: 2630040 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2090. Min Range: -6.2090
Max Act: 6.1153. Min Act: -0.1700
Data Index: 2989294 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2090. Min Range: -6.2090
Max Act: 6.0840. Min Act: -0.1700
Data Index: 3397081 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2090. Min Range: -6.2090
Max Act: 6.0528. Min Act: -0.1700
Data Index: 3901454 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.9278. Min Act: -0.1700
Data Index: 2791974 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8965. Min Act: -0.1700
Data Index: 3060756 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8965. Min Act: -0.1700
Data Index: 3348402 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8965. Min Act: -0.1700
Data Index: 741956 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8965. Min Act: -0.1700
Data Index: 3690606 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8965. Min Act: -0.1700
Data Index: 6710389 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8653. Min Act: -0.1700
Data Index: 7160175 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8653. Min Act: -0.1700
Data Index: 4308145 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8653. Min Act: -0.1700
Data Index: 7880989 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8653. Min Act: -0.1700
Data Index: 3408285 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8653. Min Act: -0.1700
Data Index: 4886527 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8340. Min Act: -0.1700
Data Index: 989554 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2090. Min Range: -6.2090
Max Act: 5.8340. Min Act: -0.1700
Data Index: 5693879 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #19