Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 20 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.7070. Min Act: -0.1700
Data Index: 4011413 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.5195. Min Act: -0.1700
Data Index: 6934573 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.5195. Min Act: -0.1700
Data Index: 5994247 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.4883. Min Act: -0.1700
Data Index: 1893039 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.5195. Min Act: -0.1700
Data Index: 2470023 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.4883. Min Act: -0.1700
Data Index: 6313452 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.4883. Min Act: -0.1700
Data Index: 463245 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.4570. Min Act: -0.1700
Data Index: 355783 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.4570. Min Act: -0.1700
Data Index: 1893036 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.4570. Min Act: -0.1700
Data Index: 7720916 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.4258. Min Act: -0.1700
Data Index: 3999739 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.4258. Min Act: -0.1700
Data Index: 5813318 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.4258. Min Act: -0.1700
Data Index: 4550878 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.3945. Min Act: -0.1700
Data Index: 5875625 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.3945. Min Act: -0.1700
Data Index: 2561168 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.3945. Min Act: -0.1700
Data Index: 2857318 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.3945. Min Act: -0.1700
Data Index: 3758947 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.3633. Min Act: -0.1700
Data Index: 7508706 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.3320. Min Act: -0.1700
Data Index: 6445448 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7070. Min Range: -6.7070
Max Act: 6.3008. Min Act: -0.1700
Data Index: 4550877 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19