Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 433 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.9605. Min Act: -0.1700
Data Index: 4338697 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.8667. Min Act: -0.1700
Data Index: 4469479 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.5542. Min Act: -0.1700
Data Index: 6215405 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.5542. Min Act: -0.1700
Data Index: 5515737 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.5542. Min Act: -0.1700
Data Index: 5408810 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.4292. Min Act: -0.1700
Data Index: 6098221 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.4605. Min Act: -0.1700
Data Index: 4766802 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.4292. Min Act: -0.1700
Data Index: 636307 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.4605. Min Act: -0.1700
Data Index: 2467754 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.4292. Min Act: -0.1700
Data Index: 203337 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.3980. Min Act: -0.1700
Data Index: 3495717 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.3667. Min Act: -0.1700
Data Index: 5189054 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.3355. Min Act: -0.1700
Data Index: 2188448 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.3355. Min Act: -0.1700
Data Index: 5035414 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.3980. Min Act: -0.1700
Data Index: 846643 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.3667. Min Act: -0.1700
Data Index: 8125757 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.3355. Min Act: -0.1700
Data Index: 6747636 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.3667. Min Act: -0.1700
Data Index: 997202 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.3355. Min Act: -0.1700
Data Index: 1593281 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9605. Min Range: -5.9605
Max Act: 5.3355. Min Act: -0.1700
Data Index: 4971273 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19