Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2856 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.7247. Min Act: -0.1700
Data Index: 3485443 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.5372. Min Act: -0.1700
Data Index: 4843150 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.4747. Min Act: -0.1700
Data Index: 641778 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.4747. Min Act: -0.1700
Data Index: 4803567 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.4747. Min Act: -0.1700
Data Index: 551964 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.4747. Min Act: -0.1700
Data Index: 423373 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.4434. Min Act: -0.1700
Data Index: 2373917 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.3809. Min Act: -0.1700
Data Index: 318819 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.3809. Min Act: -0.1700
Data Index: 6938122 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.3497. Min Act: -0.1700
Data Index: 2818041 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.3497. Min Act: -0.1700
Data Index: 928677 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2872. Min Act: -0.1700
Data Index: 1378483 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2872. Min Act: -0.1700
Data Index: 4713306 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2872. Min Act: -0.1700
Data Index: 5007716 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2872. Min Act: -0.1700
Data Index: 6048270 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2559. Min Act: -0.1700
Data Index: 5003993 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2559. Min Act: -0.1700
Data Index: 5873846 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2559. Min Act: -0.1700
Data Index: 3692151 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2559. Min Act: -0.1700
Data Index: 893505 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7247. Min Range: -5.7247
Max Act: 5.2247. Min Act: -0.1700
Data Index: 4803566 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #19