Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.3727. Min Act: -0.1700
Data Index: 407595 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.3727. Min Act: -0.1700
Data Index: 4984375 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.3102. Min Act: -0.1700
Data Index: 4527051 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.2477. Min Act: -0.1700
Data Index: 2822992 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.1226. Min Act: -0.1700
Data Index: 1220185 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.0601. Min Act: -0.1700
Data Index: 2805443 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.0601. Min Act: -0.1700
Data Index: 2500848 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.0601. Min Act: -0.1700
Data Index: 2504241 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.0289. Min Act: -0.1700
Data Index: 2101310 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.0289. Min Act: -0.1700
Data Index: 7298486 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.0289. Min Act: -0.1700
Data Index: 7902945 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3727. Min Range: -4.3727
Max Act: 4.0601. Min Act: -0.1700
Data Index: 8523051 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3727. Min Range: -4.3727
Max Act: 3.9976. Min Act: -0.1700
Data Index: 2013610 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3727. Min Range: -4.3727
Max Act: 3.9976. Min Act: -0.1700
Data Index: 7298470 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3727. Min Range: -4.3727
Max Act: 3.9976. Min Act: -0.1700
Data Index: 5787971 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3727. Min Range: -4.3727
Max Act: 3.9976. Min Act: -0.1700
Data Index: 4407789 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3727. Min Range: -4.3727
Max Act: 3.9976. Min Act: -0.1700
Data Index: 4783013 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3727. Min Range: -4.3727
Max Act: 3.9663. Min Act: -0.1700
Data Index: 4700232 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3727. Min Range: -4.3727
Max Act: 3.9663. Min Act: -0.1700
Data Index: 6710392 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3727. Min Range: -4.3727
Max Act: 3.9351. Min Act: -0.1700
Data Index: 7221328 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19