Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2890 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2689. Min Range: -7.2689
Max Act: 7.2689. Min Act: -0.1700
Data Index: 1420916 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2689. Min Range: -7.2689
Max Act: 7.1439. Min Act: -0.1700
Data Index: 54085 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2689. Min Range: -7.2689
Max Act: 7.1126. Min Act: -0.1700
Data Index: 7926951 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2689. Min Range: -7.2689
Max Act: 7.0501. Min Act: -0.1700
Data Index: 39561 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2689. Min Range: -7.2689
Max Act: 7.0189. Min Act: -0.1700
Data Index: 4175501 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.9251. Min Act: -0.1700
Data Index: 2994120 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.9564. Min Act: -0.1700
Data Index: 1577363 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.8939. Min Act: -0.1700
Data Index: 2045613 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.8939. Min Act: -0.1700
Data Index: 4176275 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.8626. Min Act: -0.1700
Data Index: 2725166 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.8626. Min Act: -0.1700
Data Index: 1501410 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.8001. Min Act: -0.1700
Data Index: 5505392 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.6751. Min Act: -0.1700
Data Index: 8137649 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.7064. Min Act: -0.1700
Data Index: 1538040 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.6751. Min Act: -0.1700
Data Index: 2194538 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.6751. Min Act: -0.1700
Data Index: 5077191 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.6751. Min Act: -0.1700
Data Index: 615863 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.6751. Min Act: -0.1700
Data Index: 3397563 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.6439. Min Act: -0.1700
Data Index: 5816515 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2689. Min Range: -7.2689
Max Act: 6.6751. Min Act: -0.1700
Data Index: 1258537 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #19