Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5266 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6928. Min Act: -0.1700
Data Index: 1492479 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.6303. Min Act: -0.1700
Data Index: 6843864 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5678. Min Act: -0.1700
Data Index: 1762295 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5678. Min Act: -0.1700
Data Index: 537452 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.5053. Min Act: -0.1700
Data Index: 412085 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4740. Min Act: -0.1700
Data Index: 2125294 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4740. Min Act: -0.1700
Data Index: 206615 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4740. Min Act: -0.1700
Data Index: 7353149 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4740. Min Act: -0.1700
Data Index: 4902365 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4740. Min Act: -0.1700
Data Index: 7762441 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4740. Min Act: -0.1700
Data Index: 8352125 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 3497222 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 5610328 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 5549831 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4740. Min Act: -0.1700
Data Index: 4902366 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 4075662 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4740. Min Act: -0.1700
Data Index: 2372992 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4428. Min Act: -0.1700
Data Index: 4475799 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4115. Min Act: -0.1700
Data Index: 5494955 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6928. Min Range: -5.6928
Max Act: 5.4115. Min Act: -0.1700
Data Index: 1253186 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19