Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1009 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.4208. Min Act: -0.1700
Data Index: 136333 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.4208. Min Act: -0.1700
Data Index: 4313453 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.3583. Min Act: -0.1700
Data Index: 270340 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.2958. Min Act: -0.1700
Data Index: 3674674 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.1395. Min Act: -0.1700
Data Index: 4975580 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.1083. Min Act: -0.1700
Data Index: 6149633 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.0458. Min Act: -0.1700
Data Index: 8045609 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.0458. Min Act: -0.1700
Data Index: 1360632 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.0458. Min Act: -0.1700
Data Index: 7293094 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.0458. Min Act: -0.1700
Data Index: 2985441 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4208. Min Range: -6.4208
Max Act: 6.0145. Min Act: -0.1700
Data Index: 2926549 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4208. Min Range: -6.4208
Max Act: 5.9833. Min Act: -0.1700
Data Index: 1935434 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4208. Min Range: -6.4208
Max Act: 5.9520. Min Act: -0.1700
Data Index: 1913909 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4208. Min Range: -6.4208
Max Act: 5.8895. Min Act: -0.1700
Data Index: 8700102 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4208. Min Range: -6.4208
Max Act: 5.9520. Min Act: -0.1700
Data Index: 8061958 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4208. Min Range: -6.4208
Max Act: 5.9520. Min Act: -0.1700
Data Index: 8395698 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4208. Min Range: -6.4208
Max Act: 5.9208. Min Act: -0.1700
Data Index: 4717898 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4208. Min Range: -6.4208
Max Act: 5.9208. Min Act: -0.1700
Data Index: 5076783 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4208. Min Range: -6.4208
Max Act: 5.8895. Min Act: -0.1700
Data Index: 6297105 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4208. Min Range: -6.4208
Max Act: 5.8895. Min Act: -0.1700
Data Index: 2327434 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19