Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3330 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0821. Min Range: -8.0821
Max Act: 8.0821. Min Act: -0.1700
Data Index: 5269175 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.9571. Min Act: -0.1700
Data Index: 1355031 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.8946. Min Act: -0.1700
Data Index: 4949075 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.8946. Min Act: -0.1700
Data Index: 1221647 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.8946. Min Act: -0.1700
Data Index: 3318339 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.8946. Min Act: -0.1700
Data Index: 1217099 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.8321. Min Act: -0.1700
Data Index: 5303918 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.7696. Min Act: -0.1700
Data Index: 6643045 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.8321. Min Act: -0.1700
Data Index: 4141238 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.7696. Min Act: -0.1700
Data Index: 8195441 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.7071. Min Act: -0.1700
Data Index: 2522716 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.6446. Min Act: -0.1700
Data Index: 6330805 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.7071. Min Act: -0.1700
Data Index: 5807510 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.7071. Min Act: -0.1700
Data Index: 158706 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.7071. Min Act: -0.1700
Data Index: 8685854 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.7071. Min Act: -0.1700
Data Index: 8354592 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.6446. Min Act: -0.1700
Data Index: 5335112 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.6446. Min Act: -0.1700
Data Index: 1902217 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.6446. Min Act: -0.1700
Data Index: 4177156 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0821. Min Range: -8.0821
Max Act: 7.6446. Min Act: -0.1700
Data Index: 2479365 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19