Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 3070 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.7542. Min Range: -9.7542
Max Act: 9.7542. Min Act: -0.1700
Data Index: 1117933 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7542. Min Range: -9.7542
Max Act: 9.1917. Min Act: -0.1700
Data Index: 2707059 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7542. Min Range: -9.7542
Max Act: 9.0667. Min Act: -0.1700
Data Index: 1332427 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7542. Min Range: -9.7542
Max Act: 9.0042. Min Act: -0.1700
Data Index: 4499958 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.9417. Min Act: -0.1700
Data Index: 5002585 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7542. Min Range: -9.7542
Max Act: 9.0042. Min Act: -0.1700
Data Index: 4135034 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.9417. Min Act: -0.1700
Data Index: 4608540 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.9417. Min Act: -0.1700
Data Index: 6455820 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.8167. Min Act: -0.1700
Data Index: 5347885 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.8792. Min Act: -0.1700
Data Index: 770476 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.8792. Min Act: -0.1700
Data Index: 4345235 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.8792. Min Act: -0.1700
Data Index: 6742737 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.8792. Min Act: -0.1700
Data Index: 3759996 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.7542. Min Act: -0.1700
Data Index: 1912698 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.6917. Min Act: -0.1700
Data Index: 2887744 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.8167. Min Act: -0.1700
Data Index: 6119978 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.6917. Min Act: -0.1700
Data Index: 7183976 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.6917. Min Act: -0.1700
Data Index: 7972647 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.7542. Min Act: -0.1700
Data Index: 7480375 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7542. Min Range: -9.7542
Max Act: 8.6917. Min Act: -0.1700
Data Index: 3402528 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19