Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3045 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.4322. Min Act: -0.1700
Data Index: 2422112 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.4634. Min Act: -0.1700
Data Index: 2722048 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.4322. Min Act: -0.1700
Data Index: 8762279 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.4009. Min Act: -0.1700
Data Index: 2422110 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.3384. Min Act: -0.1700
Data Index: 5278675 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.3384. Min Act: -0.1700
Data Index: 2789012 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.3384. Min Act: -0.1700
Data Index: 7790591 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.3072. Min Act: -0.1700
Data Index: 2714226 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.2759. Min Act: -0.1700
Data Index: 3600074 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.2759. Min Act: -0.1700
Data Index: 8094672 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.3072. Min Act: -0.1700
Data Index: 7540197 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.2447. Min Act: -0.1700
Data Index: 551319 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.2447. Min Act: -0.1700
Data Index: 2640717 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.2134. Min Act: -0.1700
Data Index: 3270601 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.1509. Min Act: -0.1700
Data Index: 2645040 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.1509. Min Act: -0.1700
Data Index: 288543 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.1197. Min Act: -0.1700
Data Index: 2659716 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.1197. Min Act: -0.1700
Data Index: 1767452 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.1197. Min Act: -0.1700
Data Index: 1767453 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4634. Min Range: -6.4634
Max Act: 6.1197. Min Act: -0.1700
Data Index: 2782505 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19