Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3120 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.6475. Min Act: -0.1700
Data Index: 8540034 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.6163. Min Act: -0.1700
Data Index: 3715764 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.5225. Min Act: -0.1700
Data Index: 8405960 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.5538. Min Act: -0.1700
Data Index: 2182051 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.4913. Min Act: -0.1700
Data Index: 6102165 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.4288. Min Act: -0.1700
Data Index: 5009605 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.4288. Min Act: -0.1700
Data Index: 7659828 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.3975. Min Act: -0.1700
Data Index: 8697507 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.3975. Min Act: -0.1700
Data Index: 1269375 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.3350. Min Act: -0.1700
Data Index: 2672689 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.3038. Min Act: -0.1700
Data Index: 2530956 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.3038. Min Act: -0.1700
Data Index: 8246896 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.2725. Min Act: -0.1700
Data Index: 224534 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.2725. Min Act: -0.1700
Data Index: 253023 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.2413. Min Act: -0.1700
Data Index: 2417914 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.2413. Min Act: -0.1700
Data Index: 5936718 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.2413. Min Act: -0.1700
Data Index: 8784836 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.2413. Min Act: -0.1700
Data Index: 7565669 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.2100. Min Act: -0.1700
Data Index: 2474345 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6475. Min Range: -7.6475
Max Act: 7.2100. Min Act: -0.1700
Data Index: 2100641 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19