Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2146 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0461. Min Range: -7.0461
Max Act: 7.0461. Min Act: -0.1700
Data Index: 7999343 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0461. Min Range: -7.0461
Max Act: 7.0461. Min Act: -0.1700
Data Index: 209794 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.9836. Min Act: -0.1700
Data Index: 1304731 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.9524. Min Act: -0.1700
Data Index: 5011212 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.8586. Min Act: -0.1700
Data Index: 7482952 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.8899. Min Act: -0.1700
Data Index: 3519924 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.8274. Min Act: -0.1700
Data Index: 6212354 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.8274. Min Act: -0.1700
Data Index: 5722504 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.7336. Min Act: -0.1700
Data Index: 6760185 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.7024. Min Act: -0.1700
Data Index: 7112083 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.7024. Min Act: -0.1700
Data Index: 1494973 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.6399. Min Act: -0.1700
Data Index: 3190020 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.5461. Min Act: -0.1700
Data Index: 6247005 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.6086. Min Act: -0.1700
Data Index: 3893673 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.6086. Min Act: -0.1700
Data Index: 8377513 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.5774. Min Act: -0.1700
Data Index: 7727875 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.5461. Min Act: -0.1700
Data Index: 3862928 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.5461. Min Act: -0.1700
Data Index: 8033909 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.5149. Min Act: -0.1700
Data Index: 5906553 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0461. Min Range: -7.0461
Max Act: 6.5461. Min Act: -0.1700
Data Index: 4726575 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19