Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5321 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.4687. Min Act: -0.1700
Data Index: 3617262 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.4062. Min Act: -0.1700
Data Index: 6336162 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.3749. Min Act: -0.1700
Data Index: 736548 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.3749. Min Act: -0.1700
Data Index: 8253610 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.3124. Min Act: -0.1700
Data Index: 2870044 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.3124. Min Act: -0.1700
Data Index: 843416 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.3124. Min Act: -0.1700
Data Index: 8798257 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2812. Min Act: -0.1700
Data Index: 4624659 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2812. Min Act: -0.1700
Data Index: 6933989 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2812. Min Act: -0.1700
Data Index: 3954887 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2499. Min Act: -0.1700
Data Index: 7044589 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2499. Min Act: -0.1700
Data Index: 3246864 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2499. Min Act: -0.1700
Data Index: 2870037 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2499. Min Act: -0.1700
Data Index: 1745054 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2187. Min Act: -0.1700
Data Index: 1414093 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2187. Min Act: -0.1700
Data Index: 56649 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2187. Min Act: -0.1700
Data Index: 6494614 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.2187. Min Act: -0.1700
Data Index: 5202066 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.1874. Min Act: -0.1700
Data Index: 2498299 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4687. Min Range: -6.4687
Max Act: 6.1874. Min Act: -0.1700
Data Index: 1385077 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #19