Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 923 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.5782. Min Act: -0.1700
Data Index: 3410993 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.4532. Min Act: -0.1700
Data Index: 8654796 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.3907. Min Act: -0.1700
Data Index: 4897740 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.3282. Min Act: -0.1700
Data Index: 7382304 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.3282. Min Act: -0.1700
Data Index: 6546224 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.3282. Min Act: -0.1700
Data Index: 928581 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.3282. Min Act: -0.1700
Data Index: 2031962 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.3595. Min Act: -0.1700
Data Index: 6165239 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.3282. Min Act: -0.1700
Data Index: 4397661 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2970. Min Act: -0.1700
Data Index: 6541212 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2657. Min Act: -0.1700
Data Index: 1697732 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2970. Min Act: -0.1700
Data Index: 2221120 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2657. Min Act: -0.1699
Data Index: 1275791 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2970. Min Act: -0.1700
Data Index: 7023580 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2345. Min Act: -0.1700
Data Index: 7504934 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2657. Min Act: -0.1700
Data Index: 2716300 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2657. Min Act: -0.1700
Data Index: 4189281 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2657. Min Act: -0.1700
Data Index: 8053942 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2657. Min Act: -0.1700
Data Index: 8186515 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5782. Min Range: -5.5782
Max Act: 5.2657. Min Act: -0.1700
Data Index: 4321526 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19