Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2526 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.7275. Min Act: -0.1700
Data Index: 4654530 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.7275. Min Act: -0.1700
Data Index: 6843489 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.6962. Min Act: -0.1700
Data Index: 7902562 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.6650. Min Act: -0.1700
Data Index: 1361742 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.6650. Min Act: -0.1700
Data Index: 2726270 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.6650. Min Act: -0.1700
Data Index: 2196387 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.5712. Min Act: -0.1700
Data Index: 4065824 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.5712. Min Act: -0.1700
Data Index: 2571345 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.5712. Min Act: -0.1700
Data Index: 8149857 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.5087. Min Act: -0.1700
Data Index: 932692 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.5087. Min Act: -0.1700
Data Index: 1262006 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.5087. Min Act: -0.1700
Data Index: 4701864 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.4462. Min Act: -0.1700
Data Index: 194012 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.4775. Min Act: -0.1700
Data Index: 429324 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.4775. Min Act: -0.1700
Data Index: 861167 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.4462. Min Act: -0.1700
Data Index: 7831855 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.4462. Min Act: -0.1700
Data Index: 6481064 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.4462. Min Act: -0.1700
Data Index: 4476107 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.4462. Min Act: -0.1700
Data Index: 1501633 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7275. Min Range: -5.7275
Max Act: 5.4462. Min Act: -0.1700
Data Index: 7904091 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19