Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3825 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.8161. Min Act: -0.1700
Data Index: 2639395 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.6598. Min Act: -0.1700
Data Index: 1046041 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.4411. Min Act: -0.1700
Data Index: 3422582 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.4411. Min Act: -0.1700
Data Index: 8824816 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.4411. Min Act: -0.1700
Data Index: 6113381 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.4411. Min Act: -0.1700
Data Index: 6611800 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.4098. Min Act: -0.1700
Data Index: 3888482 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.4098. Min Act: -0.1700
Data Index: 4093438 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.4411. Min Act: -0.1700
Data Index: 7104446 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.3786. Min Act: -0.1700
Data Index: 7633259 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.3786. Min Act: -0.1700
Data Index: 1263040 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.3786. Min Act: -0.1700
Data Index: 1282426 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.3473. Min Act: -0.1700
Data Index: 5836527 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.3473. Min Act: -0.1700
Data Index: 2743543 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.3161. Min Act: -0.1700
Data Index: 8672186 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.3161. Min Act: -0.1700
Data Index: 4164558 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.3161. Min Act: -0.1700
Data Index: 5921326 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.2848. Min Act: -0.1700
Data Index: 894020 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.3473. Min Act: -0.1700
Data Index: 2221681 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8161. Min Range: -4.8161
Max Act: 4.2848. Min Act: -0.1700
Data Index: 2505571 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19