Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 181 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0513. Min Range: -6.0513
Max Act: 6.0513. Min Act: -0.1700
Data Index: 4926079 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.8950. Min Act: -0.1700
Data Index: 1538293 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.8638. Min Act: -0.1700
Data Index: 6494936 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.8325. Min Act: -0.1700
Data Index: 2291990 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.8013. Min Act: -0.1700
Data Index: 4038497 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.7700. Min Act: -0.1700
Data Index: 3727963 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.7388. Min Act: -0.1700
Data Index: 7506929 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.7388. Min Act: -0.1700
Data Index: 4406464 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.7388. Min Act: -0.1700
Data Index: 7371654 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.7700. Min Act: -0.1700
Data Index: 7717111 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.7075. Min Act: -0.1700
Data Index: 6100632 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.7075. Min Act: -0.1700
Data Index: 6498264 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.6763. Min Act: -0.1700
Data Index: 3771678 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.6450. Min Act: -0.1700
Data Index: 5757308 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.6450. Min Act: -0.1700
Data Index: 5781372 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.6138. Min Act: -0.1700
Data Index: 5786761 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.6138. Min Act: -0.1700
Data Index: 6879425 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.6450. Min Act: -0.1700
Data Index: 2171890 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.6763. Min Act: -0.1700
Data Index: 2064077 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0513. Min Range: -6.0513
Max Act: 5.6763. Min Act: -0.1700
Data Index: 5220051 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #19