Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.4635. Min Act: -0.1700
Data Index: 348943 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.3384. Min Act: -0.1700
Data Index: 7261792 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.2759. Min Act: -0.1700
Data Index: 8688171 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.2759. Min Act: -0.1700
Data Index: 2786310 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.2447. Min Act: -0.1700
Data Index: 1009907 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.2134. Min Act: -0.1700
Data Index: 5870747 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.2134. Min Act: -0.1700
Data Index: 7408749 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.1822. Min Act: -0.1700
Data Index: 5163296 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.1509. Min Act: -0.1700
Data Index: 5643391 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.1509. Min Act: -0.1700
Data Index: 2373639 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.1197. Min Act: -0.1700
Data Index: 8466536 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.0884. Min Act: -0.1700
Data Index: 789083 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.1197. Min Act: -0.1700
Data Index: 114446 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.0572. Min Act: -0.1700
Data Index: 6812900 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.0572. Min Act: -0.1700
Data Index: 8658964 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.0259. Min Act: -0.1700
Data Index: 6293346 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.0572. Min Act: -0.1700
Data Index: 2720636 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4635. Min Range: -4.4635
Max Act: 3.9946. Min Act: -0.1700
Data Index: 4001012 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.0259. Min Act: -0.1700
Data Index: 7020896 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4635. Min Range: -4.4635
Max Act: 4.0572. Min Act: -0.1700
Data Index: 1949988 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19