Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 28 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1131. Min Range: -6.1131
Max Act: 6.1131. Min Act: -0.1700
Data Index: 8796464 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1131. Min Range: -6.1131
Max Act: 6.0818. Min Act: -0.1700
Data Index: 8285088 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.9881. Min Act: -0.1700
Data Index: 6685861 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.9568. Min Act: -0.1700
Data Index: 5718493 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8943. Min Act: -0.1700
Data Index: 1129475 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8631. Min Act: -0.1700
Data Index: 849733 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.8006. Min Act: -0.1700
Data Index: 4486401 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.7693. Min Act: -0.1700
Data Index: 7695980 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.7068. Min Act: -0.1700
Data Index: 4537644 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.6756. Min Act: -0.1700
Data Index: 7030209 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.6131. Min Act: -0.1700
Data Index: 6116967 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.6131. Min Act: -0.1700
Data Index: 3654497 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.6443. Min Act: -0.1700
Data Index: 3977014 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.5818. Min Act: -0.1700
Data Index: 6505266 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.6131. Min Act: -0.1700
Data Index: 6923162 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.6131. Min Act: -0.1700
Data Index: 6930113 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.6131. Min Act: -0.1700
Data Index: 2179770 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.5818. Min Act: -0.1700
Data Index: 7592252 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.5818. Min Act: -0.1700
Data Index: 611563 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1131. Min Range: -6.1131
Max Act: 5.5506. Min Act: -0.1700
Data Index: 1293987 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19