Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5226 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.5351. Min Act: -0.1700
Data Index: 8448698 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.4414. Min Act: -0.1700
Data Index: 2623118 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.3164. Min Act: -0.1700
Data Index: 5627033 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.3164. Min Act: -0.1700
Data Index: 8623992 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.2539. Min Act: -0.1700
Data Index: 3819111 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.2539. Min Act: -0.1700
Data Index: 4297042 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.2539. Min Act: -0.1700
Data Index: 7406913 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.2226. Min Act: -0.1700
Data Index: 743771 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.2226. Min Act: -0.1700
Data Index: 882746 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.2226. Min Act: -0.1700
Data Index: 444930 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.1601. Min Act: -0.1700
Data Index: 1245251 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.1601. Min Act: -0.1700
Data Index: 1788952 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.1289. Min Act: -0.1700
Data Index: 6545758 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.0976. Min Act: -0.1700
Data Index: 2829837 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.1289. Min Act: -0.1700
Data Index: 1675492 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.1289. Min Act: -0.1700
Data Index: 6131972 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.0976. Min Act: -0.1700
Data Index: 3985401 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.0976. Min Act: -0.1700
Data Index: 8049817 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.0976. Min Act: -0.1700
Data Index: 8134197 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5351. Min Range: -5.5351
Max Act: 5.0664. Min Act: -0.1700
Data Index: 4737837 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19