Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4706 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4155. Min Range: -9.4155
Max Act: 9.4155. Min Act: -0.1700
Data Index: 1603430 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4155. Min Range: -9.4155
Max Act: 9.2280. Min Act: -0.1700
Data Index: 4709504 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4155. Min Range: -9.4155
Max Act: 9.1655. Min Act: -0.1700
Data Index: 4367136 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4155. Min Range: -9.4155
Max Act: 9.1030. Min Act: -0.1700
Data Index: 2119531 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4155. Min Range: -9.4155
Max Act: 9.1030. Min Act: -0.1700
Data Index: 3331970 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.9155. Min Act: -0.1700
Data Index: 1553545 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.9780. Min Act: -0.1700
Data Index: 6117346 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.8530. Min Act: -0.1700
Data Index: 6118893 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.7905. Min Act: -0.1700
Data Index: 536804 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.7280. Min Act: -0.1700
Data Index: 5009637 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.7280. Min Act: -0.1700
Data Index: 2857532 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.7280. Min Act: -0.1700
Data Index: 5395115 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.7280. Min Act: -0.1700
Data Index: 2753191 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.7280. Min Act: -0.1700
Data Index: 2207740 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.6655. Min Act: -0.1700
Data Index: 4373438 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.6655. Min Act: -0.1700
Data Index: 3443611 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.6655. Min Act: -0.1700
Data Index: 1178658 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.5405. Min Act: -0.1700
Data Index: 3525715 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.6030. Min Act: -0.1700
Data Index: 635549 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4155. Min Range: -9.4155
Max Act: 8.5405. Min Act: -0.1700
Data Index: 3869236 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19