Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.5418. Min Act: -0.1700
Data Index: 706644 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.4771. Min Act: -0.1700
Data Index: 1952969 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.4120. Min Act: -0.1700
Data Index: 8385394 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.4120. Min Act: -0.1700
Data Index: 4315567 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3957. Min Act: -0.1700
Data Index: 7209616 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3957. Min Act: -0.1700
Data Index: 1675095 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3957. Min Act: -0.1700
Data Index: 3385135 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3466. Min Act: -0.1700
Data Index: 1029348 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3630. Min Act: -0.1700
Data Index: 1163182 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3466. Min Act: -0.1700
Data Index: 7132062 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3630. Min Act: -0.1700
Data Index: 2960502 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3630. Min Act: -0.1700
Data Index: 8385379 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3466. Min Act: -0.1700
Data Index: 696320 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3302. Min Act: -0.1700
Data Index: 3408589 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3466. Min Act: -0.1700
Data Index: 6484942 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3302. Min Act: -0.1700
Data Index: 3915986 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.3138. Min Act: -0.1700
Data Index: 5754607 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.2974. Min Act: -0.1697
Data Index: 5500170 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.2974. Min Act: -0.1700
Data Index: 6783073 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5418. Min Range: -2.5418
Max Act: 2.2974. Min Act: -0.1700
Data Index: 761243 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19