Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2729 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.7040. Min Act: -0.1700
Data Index: 7748669 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3915. Min Act: -0.1700
Data Index: 6363194 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3602. Min Act: -0.1700
Data Index: 8016189 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3915. Min Act: -0.1700
Data Index: 4390841 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3602. Min Act: -0.1700
Data Index: 8769804 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.3290. Min Act: -0.1700
Data Index: 5647431 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2977. Min Act: -0.1700
Data Index: 2661752 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2977. Min Act: -0.1700
Data Index: 1436974 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2977. Min Act: -0.1700
Data Index: 8195253 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2665. Min Act: -0.1700
Data Index: 5852682 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2665. Min Act: -0.1700
Data Index: 3902824 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2665. Min Act: -0.1700
Data Index: 7700455 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2352. Min Act: -0.1700
Data Index: 8653286 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2352. Min Act: -0.1700
Data Index: 7032971 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2352. Min Act: -0.1700
Data Index: 293366 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2352. Min Act: -0.1700
Data Index: 3198060 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2352. Min Act: -0.1700
Data Index: 8024031 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2352. Min Act: -0.1700
Data Index: 3030847 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2352. Min Act: -0.1700
Data Index: 6344763 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7040. Min Range: -6.7040
Max Act: 6.2352. Min Act: -0.1700
Data Index: 1044184 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19