Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0883. Min Range: -3.0883
Max Act: 3.0883. Min Act: -0.1700
Data Index: 1595369 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0883. Min Range: -3.0883
Max Act: 3.0568. Min Act: -0.1700
Data Index: 2634412 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0883. Min Range: -3.0883
Max Act: 3.0726. Min Act: -0.1700
Data Index: 5463389 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0883. Min Range: -3.0883
Max Act: 3.0568. Min Act: -0.1700
Data Index: 3018173 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0883. Min Range: -3.0883
Max Act: 3.0410. Min Act: -0.1700
Data Index: 6467992 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0883. Min Range: -3.0883
Max Act: 3.0094. Min Act: -0.1700
Data Index: 5391776 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0883. Min Range: -3.0883
Max Act: 3.0094. Min Act: -0.1700
Data Index: 1488940 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0883. Min Range: -3.0883
Max Act: 3.0094. Min Act: -0.1700
Data Index: 5740257 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0883. Min Range: -3.0883
Max Act: 3.0252. Min Act: -0.1700
Data Index: 4048462 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0883. Min Range: -3.0883
Max Act: 2.9936. Min Act: -0.1700
Data Index: 6863209 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0883. Min Range: -3.0883
Max Act: 3.0094. Min Act: -0.1700
Data Index: 1049856 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0883. Min Range: -3.0883
Max Act: 2.9936. Min Act: -0.1700
Data Index: 7659108 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0883. Min Range: -3.0883
Max Act: 2.9936. Min Act: -0.1700
Data Index: 7955152 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0883. Min Range: -3.0883
Max Act: 2.9778. Min Act: -0.1700
Data Index: 8474057 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0883. Min Range: -3.0883
Max Act: 2.9778. Min Act: -0.1700
Data Index: 162503 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0883. Min Range: -3.0883
Max Act: 2.9936. Min Act: -0.1700
Data Index: 8276243 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0883. Min Range: -3.0883
Max Act: 2.9778. Min Act: -0.1700
Data Index: 8617636 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0883. Min Range: -3.0883
Max Act: 2.9778. Min Act: -0.1700
Data Index: 5962907 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0883. Min Range: -3.0883
Max Act: 2.9620. Min Act: -0.1700
Data Index: 614823 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0883. Min Range: -3.0883
Max Act: 2.9462. Min Act: -0.1700
Data Index: 4357333 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19