Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3547 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0056. Min Range: -9.0056
Max Act: 9.0056. Min Act: -0.1700
Data Index: 3182287 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.6931. Min Act: -0.1700
Data Index: 1306756 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.5056. Min Act: -0.1700
Data Index: 4696103 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.4431. Min Act: -0.1700
Data Index: 6040792 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.5056. Min Act: -0.1700
Data Index: 8145675 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.5056. Min Act: -0.1700
Data Index: 472988 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.4431. Min Act: -0.1700
Data Index: 4312343 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.3181. Min Act: -0.1700
Data Index: 7342892 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.3806. Min Act: -0.1700
Data Index: 6906307 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.2869. Min Act: -0.1700
Data Index: 7149065 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.2556. Min Act: -0.1700
Data Index: 3748309 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.2556. Min Act: -0.1700
Data Index: 6618744 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.1931. Min Act: -0.1700
Data Index: 2278552 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.2556. Min Act: -0.1700
Data Index: 5981874 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.1931. Min Act: -0.1700
Data Index: 787275 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.1931. Min Act: -0.1700
Data Index: 5660040 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.1931. Min Act: -0.1700
Data Index: 7362313 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.1619. Min Act: -0.1700
Data Index: 7111604 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.1931. Min Act: -0.1700
Data Index: 1681288 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0056. Min Range: -9.0056
Max Act: 8.1619. Min Act: -0.1700
Data Index: 3456416 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19