Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2128 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.9044. Min Act: -0.1700
Data Index: 553274 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.8731. Min Act: -0.1700
Data Index: 1665079 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7480. Min Act: -0.1700
Data Index: 5500080 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7636. Min Act: -0.1700
Data Index: 5500079 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7480. Min Act: -0.1700
Data Index: 8066424 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7480. Min Act: -0.1700
Data Index: 5721445 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7480. Min Act: -0.1700
Data Index: 3661069 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7167. Min Act: -0.1700
Data Index: 7869984 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7011. Min Act: -0.1700
Data Index: 7870002 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7167. Min Act: -0.1700
Data Index: 7869982 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7167. Min Act: -0.1700
Data Index: 7869998 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7167. Min Act: -0.1700
Data Index: 6821540 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7011. Min Act: -0.1700
Data Index: 4194316 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.7167. Min Act: -0.1700
Data Index: 7869999 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.6854. Min Act: -0.1700
Data Index: 2718624 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.6698. Min Act: -0.1700
Data Index: 5739748 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.6854. Min Act: -0.1700
Data Index: 7727811 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.6698. Min Act: -0.1700
Data Index: 7264704 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.6698. Min Act: -0.1700
Data Index: 4610253 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9044. Min Range: -3.9044
Max Act: 3.6698. Min Act: -0.1700
Data Index: 6454316 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19