Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3119 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.2583. Min Act: -0.1700
Data Index: 8790977 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.1020. Min Act: -0.1700
Data Index: 2727861 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.1020. Min Act: -0.1700
Data Index: 585541 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.1020. Min Act: -0.1700
Data Index: 431702 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.0708. Min Act: -0.1700
Data Index: 8449023 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.0708. Min Act: -0.1700
Data Index: 4663381 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.0708. Min Act: -0.1700
Data Index: 5445673 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.0395. Min Act: -0.1700
Data Index: 3185121 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.0083. Min Act: -0.1700
Data Index: 7170822 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2583. Min Range: -7.2583
Max Act: 7.0083. Min Act: -0.1700
Data Index: 7651746 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.9770. Min Act: -0.1700
Data Index: 2626417 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.9770. Min Act: -0.1700
Data Index: 224522 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.9770. Min Act: -0.1700
Data Index: 3211589 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.9770. Min Act: -0.1700
Data Index: 224525 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.9145. Min Act: -0.1700
Data Index: 7300681 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.8833. Min Act: -0.1700
Data Index: 3124281 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.8833. Min Act: -0.1700
Data Index: 6335533 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.8833. Min Act: -0.1700
Data Index: 8301493 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.8833. Min Act: -0.1700
Data Index: 8153461 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2583. Min Range: -7.2583
Max Act: 6.8208. Min Act: -0.1700
Data Index: 3368857 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19