Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3368 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.6939. Min Act: -0.1700
Data Index: 602905 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.6314. Min Act: -0.1700
Data Index: 1451910 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.5689. Min Act: -0.1700
Data Index: 7779797 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.5689. Min Act: -0.1700
Data Index: 5715390 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.5689. Min Act: -0.1700
Data Index: 5583890 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.5064. Min Act: -0.1700
Data Index: 4118 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.4751. Min Act: -0.1700
Data Index: 7512121 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.4439. Min Act: -0.1700
Data Index: 5395105 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.4751. Min Act: -0.1700
Data Index: 5688766 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.4751. Min Act: -0.1700
Data Index: 1433101 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.4439. Min Act: -0.1700
Data Index: 5349587 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.4439. Min Act: -0.1700
Data Index: 6375571 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.4126. Min Act: -0.1700
Data Index: 2175932 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.3814. Min Act: -0.1700
Data Index: 6730868 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.3814. Min Act: -0.1700
Data Index: 2271620 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.3814. Min Act: -0.1700
Data Index: 7750516 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.3814. Min Act: -0.1700
Data Index: 7998663 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.3501. Min Act: -0.1700
Data Index: 2037393 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.3501. Min Act: -0.1700
Data Index: 7529796 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6939. Min Range: -6.6939
Max Act: 6.3501. Min Act: -0.1700
Data Index: 211553 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19