Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 831 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.3633. Min Act: -0.1700
Data Index: 3186724 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.2695. Min Act: -0.1700
Data Index: 912872 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.2383. Min Act: -0.1700
Data Index: 1647845 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.2383. Min Act: -0.1700
Data Index: 8824905 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.1133. Min Act: -0.1700
Data Index: 3301093 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.1133. Min Act: -0.1700
Data Index: 3717075 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.1133. Min Act: -0.1700
Data Index: 5661347 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.1133. Min Act: -0.1700
Data Index: 8426428 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.0820. Min Act: -0.1700
Data Index: 3301563 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.0820. Min Act: -0.1700
Data Index: 6268675 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.0508. Min Act: -0.1700
Data Index: 1856614 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.0508. Min Act: -0.1700
Data Index: 4438036 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.0508. Min Act: -0.1700
Data Index: 2983085 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.0508. Min Act: -0.1700
Data Index: 3799398 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.0195. Min Act: -0.1700
Data Index: 4130258 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3633. Min Range: -4.3633
Max Act: 4.0195. Min Act: -0.1700
Data Index: 6911592 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3633. Min Range: -4.3633
Max Act: 3.9882. Min Act: -0.1700
Data Index: 8013604 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3633. Min Range: -4.3633
Max Act: 3.9570. Min Act: -0.1700
Data Index: 3328174 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3633. Min Range: -4.3633
Max Act: 3.9882. Min Act: -0.1700
Data Index: 7360541 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3633. Min Range: -4.3633
Max Act: 3.9882. Min Act: -0.1700
Data Index: 4259261 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19