Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 478 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0638. Min Range: -5.0638
Max Act: 5.0638. Min Act: -0.1700
Data Index: 5517512 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0638. Min Range: -5.0638
Max Act: 5.0325. Min Act: -0.1700
Data Index: 674622 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0638. Min Range: -5.0638
Max Act: 5.0325. Min Act: -0.1700
Data Index: 2439553 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.9388. Min Act: -0.1700
Data Index: 5868739 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.9700. Min Act: -0.1700
Data Index: 451531 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.9388. Min Act: -0.1700
Data Index: 5679212 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.8763. Min Act: -0.1700
Data Index: 2439555 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.9075. Min Act: -0.1700
Data Index: 7444321 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.9075. Min Act: -0.1700
Data Index: 4040261 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.8763. Min Act: -0.1700
Data Index: 5679207 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.8450. Min Act: -0.1700
Data Index: 479 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.8138. Min Act: -0.1700
Data Index: 8083548 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.8138. Min Act: -0.1700
Data Index: 8448114 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.8450. Min Act: -0.1700
Data Index: 5679211 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.7513. Min Act: -0.1700
Data Index: 5679214 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.7825. Min Act: -0.1700
Data Index: 5679209 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.7513. Min Act: -0.1700
Data Index: 83378 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.7200. Min Act: -0.1700
Data Index: 5825367 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.7513. Min Act: -0.1700
Data Index: 2513452 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0638. Min Range: -5.0638
Max Act: 4.7200. Min Act: -0.1700
Data Index: 4998122 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19