Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5715 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1549. Min Range: -6.1549
Max Act: 6.1549. Min Act: -0.1700
Data Index: 5338377 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1549. Min Range: -6.1549
Max Act: 6.0612. Min Act: -0.1700
Data Index: 8579173 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.9987. Min Act: -0.1700
Data Index: 4228997 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.9674. Min Act: -0.1700
Data Index: 2882725 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.9362. Min Act: -0.1700
Data Index: 956218 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.9049. Min Act: -0.1700
Data Index: 8495864 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.8112. Min Act: -0.1700
Data Index: 7840506 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.8424. Min Act: -0.1700
Data Index: 7939571 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.8112. Min Act: -0.1700
Data Index: 5614195 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.8112. Min Act: -0.1700
Data Index: 4679394 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.8112. Min Act: -0.1700
Data Index: 5734158 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.7799. Min Act: -0.1700
Data Index: 4744965 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.7799. Min Act: -0.1700
Data Index: 4744967 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.7799. Min Act: -0.1700
Data Index: 1503528 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.7174. Min Act: -0.1700
Data Index: 6352924 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.7174. Min Act: -0.1700
Data Index: 160736 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.6862. Min Act: -0.1700
Data Index: 85549 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.7174. Min Act: -0.1700
Data Index: 624629 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.6862. Min Act: -0.1700
Data Index: 2808268 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1549. Min Range: -6.1549
Max Act: 5.6549. Min Act: -0.1700
Data Index: 169898 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #19