Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3872 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7121. Min Range: -5.7121
Max Act: 5.7121. Min Act: -0.1700
Data Index: 4747964 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7121. Min Range: -5.7121
Max Act: 5.5871. Min Act: -0.1700
Data Index: 5877725 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7121. Min Range: -5.7121
Max Act: 5.1809. Min Act: -0.1700
Data Index: 7999003 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7121. Min Range: -5.7121
Max Act: 5.1809. Min Act: -0.1700
Data Index: 5981586 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7121. Min Range: -5.7121
Max Act: 5.1184. Min Act: -0.1700
Data Index: 2595489 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7121. Min Range: -5.7121
Max Act: 5.0871. Min Act: -0.1700
Data Index: 1430358 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7121. Min Range: -5.7121
Max Act: 5.0559. Min Act: -0.1700
Data Index: 6005918 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7121. Min Range: -5.7121
Max Act: 5.0559. Min Act: -0.1700
Data Index: 5861088 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.9934. Min Act: -0.1700
Data Index: 636868 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.9621. Min Act: -0.1700
Data Index: 3628358 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.9621. Min Act: -0.1700
Data Index: 4964162 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.9621. Min Act: -0.1700
Data Index: 3531351 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.9621. Min Act: -0.1700
Data Index: 656721 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.8996. Min Act: -0.1700
Data Index: 1205718 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.9309. Min Act: -0.1700
Data Index: 2468434 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.9309. Min Act: -0.1700
Data Index: 4426508 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.8996. Min Act: -0.1700
Data Index: 2184103 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.8996. Min Act: -0.1700
Data Index: 4097941 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.8996. Min Act: -0.1700
Data Index: 4844168 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7121. Min Range: -5.7121
Max Act: 4.8996. Min Act: -0.1700
Data Index: 3362319 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #19