Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5006 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9869. Min Act: -0.1700
Data Index: 4773584 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.9557. Min Act: -0.1700
Data Index: 4557075 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8932. Min Act: -0.1700
Data Index: 761009 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8932. Min Act: -0.1700
Data Index: 7924044 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.8307. Min Act: -0.1700
Data Index: 6746030 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 8589036 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 963761 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7994. Min Act: -0.1700
Data Index: 4557074 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7682. Min Act: -0.1700
Data Index: 2181082 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7682. Min Act: -0.1700
Data Index: 7870492 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7682. Min Act: -0.1700
Data Index: 7915797 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7369. Min Act: -0.1700
Data Index: 5440957 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 6617373 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 300995 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.6744. Min Act: -0.1700
Data Index: 4206049 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 5836446 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 6644299 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 6192076 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 1109273 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9869. Min Range: -4.9869
Max Act: 4.7056. Min Act: -0.1700
Data Index: 3510395 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19