Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5902 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.4282. Min Act: -0.1700
Data Index: 539478 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.3657. Min Act: -0.1700
Data Index: 2630062 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.3345. Min Act: -0.1700
Data Index: 615466 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.3345. Min Act: -0.1700
Data Index: 3710161 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.2720. Min Act: -0.1700
Data Index: 3005434 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.2095. Min Act: -0.1700
Data Index: 367830 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.2095. Min Act: -0.1700
Data Index: 4677546 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.1782. Min Act: -0.1700
Data Index: 230415 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.1470. Min Act: -0.1700
Data Index: 4572416 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.1157. Min Act: -0.1700
Data Index: 7605455 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.0845. Min Act: -0.1700
Data Index: 1585213 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.0845. Min Act: -0.1700
Data Index: 1170899 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.0532. Min Act: -0.1700
Data Index: 8404673 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.0532. Min Act: -0.1700
Data Index: 1125869 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.0532. Min Act: -0.1700
Data Index: 2420782 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.0532. Min Act: -0.1700
Data Index: 3592836 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.0220. Min Act: -0.1700
Data Index: 5687112 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4282. Min Range: -5.4282
Max Act: 4.9907. Min Act: -0.1700
Data Index: 6700066 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4282. Min Range: -5.4282
Max Act: 4.9595. Min Act: -0.1700
Data Index: 6123666 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4282. Min Range: -5.4282
Max Act: 5.0220. Min Act: -0.1700
Data Index: 7118236 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19