Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4415 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.5076. Min Act: -0.1700
Data Index: 727980 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.4752. Min Act: -0.1700
Data Index: 3936618 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.4427. Min Act: -0.1700
Data Index: 5570164 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.4427. Min Act: -0.1700
Data Index: 6668081 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.4264. Min Act: -0.1700
Data Index: 2863551 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.4101. Min Act: -0.1700
Data Index: 1006661 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.4101. Min Act: -0.1700
Data Index: 1558972 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3775. Min Act: -0.1700
Data Index: 1828273 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3775. Min Act: -0.1700
Data Index: 5263938 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3775. Min Act: -0.1700
Data Index: 2310859 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3775. Min Act: -0.1700
Data Index: 4066083 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3611. Min Act: -0.1700
Data Index: 1268076 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3611. Min Act: -0.1700
Data Index: 6281749 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3611. Min Act: -0.1700
Data Index: 4209836 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3447. Min Act: -0.1700
Data Index: 699168 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3447. Min Act: -0.1700
Data Index: 3293706 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3611. Min Act: -0.1700
Data Index: 10529 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3611. Min Act: -0.1700
Data Index: 5464025 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3611. Min Act: -0.1700
Data Index: 6582990 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5076. Min Range: -2.5076
Max Act: 2.3611. Min Act: -0.1700
Data Index: 2069981 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19