Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5565 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.4925. Min Act: -0.1700
Data Index: 5664834 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.4300. Min Act: -0.1700
Data Index: 7586774 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.3675. Min Act: -0.1700
Data Index: 3012299 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.3675. Min Act: -0.1700
Data Index: 7095661 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.3675. Min Act: -0.1700
Data Index: 5084578 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.2425. Min Act: -0.1700
Data Index: 139112 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.3050. Min Act: -0.1700
Data Index: 5881568 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.3050. Min Act: -0.1700
Data Index: 6869016 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.3050. Min Act: -0.1700
Data Index: 58974 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.3050. Min Act: -0.1700
Data Index: 2741025 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.3050. Min Act: -0.1699
Data Index: 580969 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.3050. Min Act: -0.1700
Data Index: 5318325 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.2425. Min Act: -0.1700
Data Index: 2538103 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.2425. Min Act: -0.1700
Data Index: 7647794 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.2425. Min Act: -0.1700
Data Index: 5861719 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.2425. Min Act: -0.1700
Data Index: 1506749 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.1175. Min Act: -0.1700
Data Index: 971140 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.1175. Min Act: -0.1700
Data Index: 548142 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.1175. Min Act: -0.1700
Data Index: 635369 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4925. Min Range: -7.4925
Max Act: 7.1175. Min Act: -0.1700
Data Index: 68614 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19