Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3231 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.9280. Min Act: -0.1700
Data Index: 8185273 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.8967. Min Act: -0.1700
Data Index: 7663035 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.7716. Min Act: -0.1700
Data Index: 3371787 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.7247. Min Act: -0.1700
Data Index: 2138024 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.7091. Min Act: -0.1700
Data Index: 4832795 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6934. Min Act: -0.1700
Data Index: 3075445 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6778. Min Act: -0.1700
Data Index: 1529546 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6778. Min Act: -0.1700
Data Index: 2534066 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6778. Min Act: -0.1700
Data Index: 2043996 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6621. Min Act: -0.1700
Data Index: 7924288 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6465. Min Act: -0.1700
Data Index: 965782 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6465. Min Act: -0.1700
Data Index: 403518 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6621. Min Act: -0.1700
Data Index: 3375229 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6465. Min Act: -0.1700
Data Index: 6381408 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6465. Min Act: -0.1700
Data Index: 8756187 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.6152. Min Act: -0.1700
Data Index: 2079987 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.5839. Min Act: -0.1700
Data Index: 6518060 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.5839. Min Act: -0.1700
Data Index: 7766670 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.5682. Min Act: -0.1700
Data Index: 8348822 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9280. Min Range: -3.9280
Max Act: 3.5682. Min Act: -0.1700
Data Index: 2702018 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19