Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3812 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2450. Min Range: -5.2450
Max Act: 5.2450. Min Act: -0.1700
Data Index: 2843828 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.8388. Min Act: -0.1700
Data Index: 8237936 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.7450. Min Act: -0.1700
Data Index: 4739896 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.7138. Min Act: -0.1700
Data Index: 221480 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.6825. Min Act: -0.1700
Data Index: 8458925 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.7138. Min Act: -0.1700
Data Index: 7995898 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.6513. Min Act: -0.1700
Data Index: 8327042 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.6513. Min Act: -0.1700
Data Index: 7318814 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.6825. Min Act: -0.1700
Data Index: 8317989 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.6513. Min Act: -0.1700
Data Index: 3703287 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.6200. Min Act: -0.1700
Data Index: 1069772 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.6200. Min Act: -0.1700
Data Index: 486259 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.6513. Min Act: -0.1700
Data Index: 8458924 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.6513. Min Act: -0.1700
Data Index: 6125772 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.5888. Min Act: -0.1700
Data Index: 37074 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.5888. Min Act: -0.1700
Data Index: 6134501 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.5888. Min Act: -0.1700
Data Index: 5119420 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.5575. Min Act: -0.1700
Data Index: 6210210 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.5575. Min Act: -0.1700
Data Index: 8690621 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2450. Min Range: -5.2450
Max Act: 4.4950. Min Act: -0.1700
Data Index: 1915133 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19