Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 674 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1587. Min Range: -5.1587
Max Act: 5.1587. Min Act: -0.1700
Data Index: 7574596 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.9087. Min Act: -0.1700
Data Index: 1696155 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.8775. Min Act: -0.1700
Data Index: 3604655 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.8150. Min Act: -0.1700
Data Index: 7216266 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.7837. Min Act: -0.1700
Data Index: 774084 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.7837. Min Act: -0.1700
Data Index: 2100759 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.7837. Min Act: -0.1700
Data Index: 5921419 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.7525. Min Act: -0.1700
Data Index: 7511443 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.7212. Min Act: -0.1700
Data Index: 4597072 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.7212. Min Act: -0.1700
Data Index: 7938454 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.6900. Min Act: -0.1700
Data Index: 8191538 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.6900. Min Act: -0.1700
Data Index: 5572126 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.6900. Min Act: -0.1700
Data Index: 2896270 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.6900. Min Act: -0.1700
Data Index: 3833127 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.6900. Min Act: -0.1700
Data Index: 7963199 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.6900. Min Act: -0.1700
Data Index: 3094237 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.6900. Min Act: -0.1700
Data Index: 4555647 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.6900. Min Act: -0.1700
Data Index: 1781332 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.6900. Min Act: -0.1700
Data Index: 3367349 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1587. Min Range: -5.1587
Max Act: 4.6587. Min Act: -0.1700
Data Index: 808008 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19