Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6057 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.9684. Min Act: -0.1700
Data Index: 5691537 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.7809. Min Act: -0.1700
Data Index: 1639966 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.6559. Min Act: -0.1700
Data Index: 2290933 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.7184. Min Act: -0.1700
Data Index: 7875512 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.7184. Min Act: -0.1700
Data Index: 6456376 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.7184. Min Act: -0.1700
Data Index: 2586562 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.6559. Min Act: -0.1700
Data Index: 4515911 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.6559. Min Act: -0.1700
Data Index: 1849565 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.6559. Min Act: -0.1700
Data Index: 5160646 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5934. Min Act: -0.1700
Data Index: 6156145 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5309. Min Act: -0.1700
Data Index: 2568300 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5934. Min Act: -0.1700
Data Index: 6572385 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5934. Min Act: -0.1700
Data Index: 2318630 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5309. Min Act: -0.1700
Data Index: 2864311 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5309. Min Act: -0.1700
Data Index: 1860646 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5309. Min Act: -0.1700
Data Index: 6533155 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5309. Min Act: -0.1700
Data Index: 4252335 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5309. Min Act: -0.1700
Data Index: 2054058 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5309. Min Act: -0.1700
Data Index: 7214331 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9684. Min Range: -7.9684
Max Act: 7.5309. Min Act: -0.1700
Data Index: 7335081 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19