Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.6061. Min Act: -0.1700
Data Index: 3592540 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.4930. Min Act: -0.1700
Data Index: 3592541 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.4606. Min Act: -0.1700
Data Index: 5344466 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.4443. Min Act: -0.1700
Data Index: 7756768 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3954. Min Act: -0.1700
Data Index: 5344465 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3954. Min Act: -0.1700
Data Index: 3098089 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3954. Min Act: -0.1700
Data Index: 6399351 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3791. Min Act: -0.1700
Data Index: 6260781 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3628. Min Act: -0.1700
Data Index: 3946301 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3628. Min Act: -0.1700
Data Index: 1658045 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3791. Min Act: -0.1700
Data Index: 879190 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3628. Min Act: -0.1700
Data Index: 482465 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3628. Min Act: -0.1700
Data Index: 7307232 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3628. Min Act: -0.1700
Data Index: 6510198 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3628. Min Act: -0.1700
Data Index: 3723771 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3791. Min Act: -0.1700
Data Index: 5663471 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3300. Min Act: -0.1700
Data Index: 220729 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3300. Min Act: -0.1700
Data Index: 7583746 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3300. Min Act: -0.1700
Data Index: 487970 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6061. Min Range: -2.6061
Max Act: 2.3300. Min Act: -0.1700
Data Index: 4535575 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #19