Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3946 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.2460. Min Act: -0.1700
Data Index: 7250640 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.2147. Min Act: -0.1700
Data Index: 7169371 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.2147. Min Act: -0.1700
Data Index: 8489721 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.1835. Min Act: -0.1700
Data Index: 8542050 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.0897. Min Act: -0.1700
Data Index: 7940605 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.0897. Min Act: -0.1700
Data Index: 8294845 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.0897. Min Act: -0.1700
Data Index: 7619611 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.0585. Min Act: -0.1700
Data Index: 7080892 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.0585. Min Act: -0.1700
Data Index: 8824489 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.0272. Min Act: -0.1700
Data Index: 25269 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.0272. Min Act: -0.1700
Data Index: 7390751 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.0272. Min Act: -0.1700
Data Index: 6363949 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2460. Min Range: -5.2460
Max Act: 4.9960. Min Act: -0.1700
Data Index: 8635775 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2460. Min Range: -5.2460
Max Act: 4.9647. Min Act: -0.1700
Data Index: 7742619 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2460. Min Range: -5.2460
Max Act: 5.0272. Min Act: -0.1700
Data Index: 7010451 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2460. Min Range: -5.2460
Max Act: 4.9647. Min Act: -0.1700
Data Index: 3534460 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2460. Min Range: -5.2460
Max Act: 4.9647. Min Act: -0.1700
Data Index: 6418461 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2460. Min Range: -5.2460
Max Act: 4.9960. Min Act: -0.1700
Data Index: 7560999 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2460. Min Range: -5.2460
Max Act: 4.9960. Min Act: -0.1700
Data Index: 2864784 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2460. Min Range: -5.2460
Max Act: 4.9647. Min Act: -0.1700
Data Index: 3619648 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19