Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2524 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.4587. Min Act: -0.1700
Data Index: 8143680 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3608. Min Act: -0.1700
Data Index: 8495973 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3608. Min Act: -0.1700
Data Index: 8161549 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3444. Min Act: -0.1700
Data Index: 82926 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3608. Min Act: -0.1700
Data Index: 7622472 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3608. Min Act: -0.1700
Data Index: 5923415 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3444. Min Act: -0.1700
Data Index: 5209990 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3280. Min Act: -0.1700
Data Index: 3751141 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3444. Min Act: -0.1700
Data Index: 8491161 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3116. Min Act: -0.1700
Data Index: 5009823 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3444. Min Act: -0.1700
Data Index: 7947671 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3116. Min Act: -0.1700
Data Index: 7986028 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.2952. Min Act: -0.1700
Data Index: 2466925 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.3116. Min Act: -0.1700
Data Index: 52652 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.2952. Min Act: -0.1700
Data Index: 7687832 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.2622. Min Act: -0.1700
Data Index: 5870084 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.2622. Min Act: -0.1700
Data Index: 51412 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.2622. Min Act: -0.1700
Data Index: 1659549 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.2457. Min Act: -0.1700
Data Index: 4211181 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4587. Min Range: -2.4587
Max Act: 2.2622. Min Act: -0.1700
Data Index: 4590668 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19