Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5000 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1901. Min Range: -3.1901
Max Act: 3.1901. Min Act: -0.1700
Data Index: 4262876 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.9693. Min Act: -0.1700
Data Index: 3576584 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.9377. Min Act: -0.1700
Data Index: 548876 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.9377. Min Act: -0.1700
Data Index: 4374964 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.9377. Min Act: -0.1700
Data Index: 5063890 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.9219. Min Act: -0.1700
Data Index: 4503080 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8901. Min Act: -0.1700
Data Index: 7858140 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8743. Min Act: -0.1700
Data Index: 5258472 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8743. Min Act: -0.1700
Data Index: 740702 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8584. Min Act: -0.1700
Data Index: 8551106 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8584. Min Act: -0.1700
Data Index: 7313532 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8584. Min Act: -0.1700
Data Index: 4428507 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8425. Min Act: -0.1700
Data Index: 4031797 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8584. Min Act: -0.1700
Data Index: 5613723 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8584. Min Act: -0.1700
Data Index: 7439205 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8425. Min Act: -0.1700
Data Index: 6481582 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8266. Min Act: -0.1700
Data Index: 5501819 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8584. Min Act: -0.1700
Data Index: 1924907 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8425. Min Act: -0.1700
Data Index: 7319354 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1901. Min Range: -3.1901
Max Act: 2.8584. Min Act: -0.1700
Data Index: 1112005 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19