Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4565 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.8399. Min Act: -0.1700
Data Index: 7438732 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.7149. Min Act: -0.1700
Data Index: 2433671 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.6524. Min Act: -0.1700
Data Index: 4827337 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.4649. Min Act: -0.1700
Data Index: 8766664 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.3087. Min Act: -0.1700
Data Index: 2085017 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.2462. Min Act: -0.1700
Data Index: 561307 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.1837. Min Act: -0.1700
Data Index: 2227554 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.1212. Min Act: -0.1700
Data Index: 308086 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.1212. Min Act: -0.1700
Data Index: 4184819 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.1212. Min Act: -0.1700
Data Index: 1342731 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.0587. Min Act: -0.1700
Data Index: 4262264 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.0587. Min Act: -0.1700
Data Index: 4052151 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8399. Min Range: -6.8399
Max Act: 5.9962. Min Act: -0.1700
Data Index: 4990359 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8399. Min Range: -6.8399
Max Act: 5.9962. Min Act: -0.1700
Data Index: 2636483 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8399. Min Range: -6.8399
Max Act: 6.0274. Min Act: -0.1700
Data Index: 1308217 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8399. Min Range: -6.8399
Max Act: 5.9649. Min Act: -0.1700
Data Index: 4395319 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8399. Min Range: -6.8399
Max Act: 5.9649. Min Act: -0.1700
Data Index: 517252 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8399. Min Range: -6.8399
Max Act: 5.9337. Min Act: -0.1700
Data Index: 5054920 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8399. Min Range: -6.8399
Max Act: 5.9337. Min Act: -0.1700
Data Index: 8133124 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8399. Min Range: -6.8399
Max Act: 5.9024. Min Act: -0.1700
Data Index: 5982837 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19