Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3466 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.2776. Min Act: -0.1700
Data Index: 6667434 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.2464. Min Act: -0.1700
Data Index: 8266154 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.2151. Min Act: -0.1700
Data Index: 5497038 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.2464. Min Act: -0.1700
Data Index: 6815525 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.1526. Min Act: -0.1700
Data Index: 6751148 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.1526. Min Act: -0.1700
Data Index: 863584 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.1214. Min Act: -0.1700
Data Index: 3995212 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0901. Min Act: -0.1700
Data Index: 612924 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0901. Min Act: -0.1700
Data Index: 3515616 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0589. Min Act: -0.1700
Data Index: 4017543 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0276. Min Act: -0.1700
Data Index: 5774603 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0589. Min Act: -0.1700
Data Index: 2272554 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0589. Min Act: -0.1700
Data Index: 943811 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2776. Min Range: -6.2776
Max Act: 6.0276. Min Act: -0.1700
Data Index: 1931981 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9964. Min Act: -0.1700
Data Index: 6541416 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9651. Min Act: -0.1700
Data Index: 5267994 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9964. Min Act: -0.1700
Data Index: 6001736 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9964. Min Act: -0.1700
Data Index: 6894530 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9964. Min Act: -0.1700
Data Index: 6751149 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2776. Min Range: -6.2776
Max Act: 5.9964. Min Act: -0.1700
Data Index: 4972476 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19