Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.7038. Min Act: -0.1700
Data Index: 3861794 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.3913. Min Act: -0.1700
Data Index: 1966027 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.2663. Min Act: -0.1700
Data Index: 8781100 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.1725. Min Act: -0.1700
Data Index: 8739966 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.0788. Min Act: -0.1700
Data Index: 8053806 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.0788. Min Act: -0.1700
Data Index: 564920 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.0475. Min Act: -0.1700
Data Index: 1874531 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.0788. Min Act: -0.1700
Data Index: 4793642 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.0788. Min Act: -0.1700
Data Index: 2872812 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.0163. Min Act: -0.1700
Data Index: 3994964 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.0475. Min Act: -0.1700
Data Index: 6100279 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7038. Min Range: -7.7038
Max Act: 7.0163. Min Act: -0.1700
Data Index: 4606276 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7038. Min Range: -7.7038
Max Act: 6.9850. Min Act: -0.1700
Data Index: 3687708 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7038. Min Range: -7.7038
Max Act: 6.9850. Min Act: -0.1700
Data Index: 397451 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7038. Min Range: -7.7038
Max Act: 6.9538. Min Act: -0.1700
Data Index: 7416343 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7038. Min Range: -7.7038
Max Act: 6.9538. Min Act: -0.1700
Data Index: 5812027 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7038. Min Range: -7.7038
Max Act: 6.9538. Min Act: -0.1700
Data Index: 1084549 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7038. Min Range: -7.7038
Max Act: 6.9850. Min Act: -0.1700
Data Index: 8775950 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7038. Min Range: -7.7038
Max Act: 6.9538. Min Act: -0.1700
Data Index: 4251882 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7038. Min Range: -7.7038
Max Act: 6.9225. Min Act: -0.1700
Data Index: 1209049 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19