Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2090 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.4293. Min Act: -0.1700
Data Index: 3711159 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.3356. Min Act: -0.1700
Data Index: 6330 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.3356. Min Act: -0.1700
Data Index: 7731059 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.3043. Min Act: -0.1700
Data Index: 8128169 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.3043. Min Act: -0.1700
Data Index: 8465860 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.2731. Min Act: -0.1700
Data Index: 7310284 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.2731. Min Act: -0.1700
Data Index: 8128162 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.2418. Min Act: -0.1700
Data Index: 8465861 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.2418. Min Act: -0.1700
Data Index: 2205553 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.2418. Min Act: -0.1700
Data Index: 8128156 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.2106. Min Act: -0.1700
Data Index: 8128158 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.1793. Min Act: -0.1700
Data Index: 8235453 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.1481. Min Act: -0.1700
Data Index: 4372935 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.1481. Min Act: -0.1700
Data Index: 5635190 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.1168. Min Act: -0.1700
Data Index: 3515906 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.1168. Min Act: -0.1700
Data Index: 2205574 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.1168. Min Act: -0.1700
Data Index: 7025088 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.0855. Min Act: -0.1700
Data Index: 3393327 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.1481. Min Act: -0.1700
Data Index: 1847703 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4293. Min Range: -4.4293
Max Act: 4.1168. Min Act: -0.1700
Data Index: 1847702 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19