Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5792 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.7749. Min Act: -0.1700
Data Index: 1546136 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.7437. Min Act: -0.1700
Data Index: 4612504 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.7437. Min Act: -0.1700
Data Index: 6703401 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.6812. Min Act: -0.1700
Data Index: 6768065 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.6187. Min Act: -0.1700
Data Index: 2544593 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.5249. Min Act: -0.1700
Data Index: 3947128 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.5562. Min Act: -0.1700
Data Index: 5942013 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.5249. Min Act: -0.1700
Data Index: 6499962 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.4312. Min Act: -0.1700
Data Index: 585095 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.3999. Min Act: -0.1700
Data Index: 6872477 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.3687. Min Act: -0.1700
Data Index: 8713943 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.3374. Min Act: -0.1700
Data Index: 750646 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.3374. Min Act: -0.1700
Data Index: 6666603 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.3374. Min Act: -0.1700
Data Index: 6383787 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.3062. Min Act: -0.1700
Data Index: 4879196 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.3062. Min Act: -0.1700
Data Index: 819025 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.3062. Min Act: -0.1700
Data Index: 2667446 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.2749. Min Act: -0.1700
Data Index: 4661860 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.2749. Min Act: -0.1700
Data Index: 5189127 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7749. Min Range: -6.7749
Max Act: 6.2437. Min Act: -0.1700
Data Index: 347168 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19