Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5404 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.6524. Min Act: -0.1700
Data Index: 1013251 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.6055. Min Act: -0.1700
Data Index: 2000224 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5898. Min Act: -0.1700
Data Index: 7098420 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5742. Min Act: -0.1700
Data Index: 7513064 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5742. Min Act: -0.1700
Data Index: 107355 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5585. Min Act: -0.1700
Data Index: 7001563 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5585. Min Act: -0.1700
Data Index: 7120574 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5429. Min Act: -0.1700
Data Index: 91000 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5429. Min Act: -0.1700
Data Index: 1541151 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5272. Min Act: -0.1700
Data Index: 1462547 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5272. Min Act: -0.1700
Data Index: 7098421 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5429. Min Act: -0.1700
Data Index: 4530878 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5429. Min Act: -0.1700
Data Index: 7242505 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5429. Min Act: -0.1700
Data Index: 1906644 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5272. Min Act: -0.1700
Data Index: 3392807 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5272. Min Act: -0.1700
Data Index: 1354124 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5272. Min Act: -0.1700
Data Index: 1915456 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5272. Min Act: -0.1700
Data Index: 138873 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5115. Min Act: -0.1700
Data Index: 5250104 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6524. Min Range: -3.6524
Max Act: 3.5272. Min Act: -0.1700
Data Index: 224670 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19