Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3759 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2353. Min Range: -8.2353
Max Act: 8.2353. Min Act: -0.1700
Data Index: 5844541 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2353. Min Range: -8.2353
Max Act: 8.1728. Min Act: -0.1700
Data Index: 174015 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2353. Min Range: -8.2353
Max Act: 8.1728. Min Act: -0.1700
Data Index: 4277521 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2353. Min Range: -8.2353
Max Act: 8.1103. Min Act: -0.1700
Data Index: 4971894 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2353. Min Range: -8.2353
Max Act: 8.1728. Min Act: -0.1700
Data Index: 2492754 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.9853. Min Act: -0.1700
Data Index: 6874474 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2353. Min Range: -8.2353
Max Act: 8.0478. Min Act: -0.1700
Data Index: 5426043 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.9853. Min Act: -0.1700
Data Index: 7121469 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.9853. Min Act: -0.1700
Data Index: 7007355 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.9853. Min Act: -0.1700
Data Index: 8475499 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.9853. Min Act: -0.1700
Data Index: 2805405 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.9853. Min Act: -0.1700
Data Index: 2936920 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.9853. Min Act: -0.1700
Data Index: 1615658 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2353. Min Range: -8.2353
Max Act: 8.0478. Min Act: -0.1700
Data Index: 4617197 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.9853. Min Act: -0.1700
Data Index: 2663477 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.8603. Min Act: -0.1700
Data Index: 5451758 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.8603. Min Act: -0.1700
Data Index: 556959 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.8603. Min Act: -0.1700
Data Index: 4526260 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.8603. Min Act: -0.1700
Data Index: 1435498 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2353. Min Range: -8.2353
Max Act: 7.8603. Min Act: -0.1700
Data Index: 3251523 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19