Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5772 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3545. Min Range: -8.3545
Max Act: 8.3545. Min Act: -0.1700
Data Index: 29447 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3545. Min Range: -8.3545
Max Act: 7.8233. Min Act: -0.1700
Data Index: 5759661 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.9483. Min Act: -0.1700
Data Index: 2579922 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.9483. Min Act: -0.1700
Data Index: 6295800 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.9170. Min Act: -0.1700
Data Index: 104693 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.9170. Min Act: -0.1700
Data Index: 3012236 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.8858. Min Act: -0.1700
Data Index: 6215692 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.8545. Min Act: -0.1700
Data Index: 703099 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.8233. Min Act: -0.1700
Data Index: 2259639 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.8233. Min Act: -0.1700
Data Index: 2162267 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.7608. Min Act: -0.1700
Data Index: 4537977 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.7295. Min Act: -0.1700
Data Index: 8824920 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.6670. Min Act: -0.1700
Data Index: 2472000 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.6983. Min Act: -0.1700
Data Index: 5471788 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.6983. Min Act: -0.1700
Data Index: 8617306 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.6670. Min Act: -0.1700
Data Index: 4058573 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.6670. Min Act: -0.1700
Data Index: 4544533 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.6358. Min Act: -0.1700
Data Index: 1984346 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.6358. Min Act: -0.1700
Data Index: 4025515 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3545. Min Range: -8.3545
Max Act: 6.6045. Min Act: -0.1700
Data Index: 7007972 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19