Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 667 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.4545. Min Act: -0.1700
Data Index: 8086274 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.3295. Min Act: -0.1700
Data Index: 3386837 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.2670. Min Act: -0.1700
Data Index: 3137215 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.2670. Min Act: -0.1700
Data Index: 1667646 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.2357. Min Act: -0.1700
Data Index: 4656000 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.2357. Min Act: -0.1700
Data Index: 710594 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.2357. Min Act: -0.1700
Data Index: 4803839 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.1420. Min Act: -0.1700
Data Index: 2180745 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.1420. Min Act: -0.1700
Data Index: 8152207 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.1107. Min Act: -0.1700
Data Index: 3150329 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.0795. Min Act: -0.1700
Data Index: 5370285 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.0795. Min Act: -0.1700
Data Index: 1531957 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.1420. Min Act: -0.1700
Data Index: 1262316 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.0795. Min Act: -0.1700
Data Index: 325413 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.0795. Min Act: -0.1700
Data Index: 1523383 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.0795. Min Act: -0.1700
Data Index: 1055187 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.0482. Min Act: -0.1700
Data Index: 2750677 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.0795. Min Act: -0.1700
Data Index: 626236 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.0482. Min Act: -0.1700
Data Index: 6257306 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4545. Min Range: -5.4545
Max Act: 5.0795. Min Act: -0.1700
Data Index: 5402465 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19