Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2311 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.4455. Min Act: -0.1700
Data Index: 7487773 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.4455. Min Act: -0.1700
Data Index: 4085401 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.3518. Min Act: -0.1700
Data Index: 1911368 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.3205. Min Act: -0.1700
Data Index: 3252676 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.3205. Min Act: -0.1700
Data Index: 5594337 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.3205. Min Act: -0.1700
Data Index: 5443321 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2580. Min Act: -0.1700
Data Index: 1146108 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2580. Min Act: -0.1700
Data Index: 4905697 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2268. Min Act: -0.1700
Data Index: 2633485 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2268. Min Act: -0.1700
Data Index: 6641084 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.2268. Min Act: -0.1700
Data Index: 6169455 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1955. Min Act: -0.1700
Data Index: 2935110 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1955. Min Act: -0.1700
Data Index: 7425756 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1955. Min Act: -0.1700
Data Index: 1856930 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1643. Min Act: -0.1700
Data Index: 554474 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1643. Min Act: -0.1699
Data Index: 1754953 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1643. Min Act: -0.1700
Data Index: 7511141 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1330. Min Act: -0.1700
Data Index: 2195540 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.1330. Min Act: -0.1700
Data Index: 8618286 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4455. Min Range: -6.4455
Max Act: 6.0705. Min Act: -0.1700
Data Index: 173659 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19