Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4399 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.3973. Min Act: -0.1700
Data Index: 5988510 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.3035. Min Act: -0.1700
Data Index: 447309 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.2723. Min Act: -0.1700
Data Index: 4771263 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.2410. Min Act: -0.1700
Data Index: 1356762 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1785. Min Act: -0.1700
Data Index: 3145933 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1785. Min Act: -0.1700
Data Index: 1550892 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1785. Min Act: -0.1700
Data Index: 6549211 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1473. Min Act: -0.1700
Data Index: 8523175 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1160. Min Act: -0.1700
Data Index: 226769 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1473. Min Act: -0.1700
Data Index: 5085029 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1160. Min Act: -0.1700
Data Index: 978807 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.0848. Min Act: -0.1700
Data Index: 4462346 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1473. Min Act: -0.1700
Data Index: 8608851 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1160. Min Act: -0.1700
Data Index: 5614458 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.0848. Min Act: -0.1700
Data Index: 4735428 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1160. Min Act: -0.1700
Data Index: 1733127 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.0848. Min Act: -0.1700
Data Index: 7384262 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.1160. Min Act: -0.1700
Data Index: 5976706 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.0848. Min Act: -0.1700
Data Index: 3745880 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3973. Min Range: -5.3973
Max Act: 5.0223. Min Act: -0.1700
Data Index: 65588 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19