Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3298 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.6461. Min Act: -0.1700
Data Index: 7090343 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.5836. Min Act: -0.1700
Data Index: 1969803 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.5836. Min Act: -0.1697
Data Index: 6907295 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.5524. Min Act: -0.1700
Data Index: 4782044 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.5524. Min Act: -0.1700
Data Index: 8195419 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.5211. Min Act: -0.1700
Data Index: 5487429 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.5524. Min Act: -0.1700
Data Index: 6253837 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4899. Min Act: -0.1700
Data Index: 4999037 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.5211. Min Act: -0.1700
Data Index: 6651154 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4899. Min Act: -0.1700
Data Index: 6539442 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4899. Min Act: -0.1689
Data Index: 1826587 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4899. Min Act: -0.1699
Data Index: 1724391 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4586. Min Act: -0.1699
Data Index: 1219669 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4899. Min Act: -0.1700
Data Index: 4449097 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4586. Min Act: -0.1699
Data Index: 8557592 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4586. Min Act: -0.1700
Data Index: 7581459 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4274. Min Act: -0.1700
Data Index: 1007871 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4274. Min Act: -0.1700
Data Index: 4269625 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4274. Min Act: -0.1694
Data Index: 370518 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6461. Min Range: -5.6461
Max Act: 5.4274. Min Act: -0.1700
Data Index: 4470323 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19