Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5802 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.8710. Min Act: -0.1700
Data Index: 1643254 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.8085. Min Act: -0.1700
Data Index: 2030747 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.7147. Min Act: -0.1700
Data Index: 2256509 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.6835. Min Act: -0.1700
Data Index: 8355280 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5897. Min Act: -0.1700
Data Index: 8377534 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5585. Min Act: -0.1700
Data Index: 7496428 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5272. Min Act: -0.1700
Data Index: 634375 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5272. Min Act: -0.1700
Data Index: 3236872 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5272. Min Act: -0.1700
Data Index: 5130958 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.5272. Min Act: -0.1700
Data Index: 1800545 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4960. Min Act: -0.1700
Data Index: 4054833 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4960. Min Act: -0.1700
Data Index: 1842575 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4960. Min Act: -0.1700
Data Index: 3692645 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4960. Min Act: -0.1700
Data Index: 72120 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4960. Min Act: -0.1700
Data Index: 3304437 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4960. Min Act: -0.1700
Data Index: 4513368 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4647. Min Act: -0.1700
Data Index: 7410601 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4335. Min Act: -0.1700
Data Index: 1264020 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4647. Min Act: -0.1700
Data Index: 4274060 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8710. Min Range: -6.8710
Max Act: 6.4647. Min Act: -0.1700
Data Index: 4363421 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19