Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1226 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.7020. Min Act: -0.1700
Data Index: 387431 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.6708. Min Act: -0.1700
Data Index: 3564514 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.6708. Min Act: -0.1700
Data Index: 2019963 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5145. Min Act: -0.1700
Data Index: 5080846 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.5145. Min Act: -0.1700
Data Index: 5993409 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4208. Min Act: -0.1700
Data Index: 3614227 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.4520. Min Act: -0.1700
Data Index: 7177468 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3583. Min Act: -0.1700
Data Index: 4867460 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3583. Min Act: -0.1700
Data Index: 6657794 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.3270. Min Act: -0.1700
Data Index: 6746680 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2958. Min Act: -0.1700
Data Index: 7026973 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2958. Min Act: -0.1700
Data Index: 5150063 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2958. Min Act: -0.1700
Data Index: 3608731 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2958. Min Act: -0.1700
Data Index: 2178981 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2333. Min Act: -0.1700
Data Index: 4134026 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2333. Min Act: -0.1700
Data Index: 587740 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2020. Min Act: -0.1700
Data Index: 2871313 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2020. Min Act: -0.1700
Data Index: 5290130 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2020. Min Act: -0.1700
Data Index: 2112859 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7020. Min Range: -5.7020
Max Act: 5.2020. Min Act: -0.1700
Data Index: 231326 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19