Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 693 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.3077. Min Act: -0.1700
Data Index: 3434315 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.2764. Min Act: -0.1699
Data Index: 4925508 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.2139. Min Act: -0.1700
Data Index: 3228186 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.2139. Min Act: -0.1700
Data Index: 8765406 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.1827. Min Act: -0.1700
Data Index: 4511867 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.1827. Min Act: -0.1697
Data Index: 461763 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0889. Min Act: -0.1699
Data Index: 304814 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.1202. Min Act: -0.1700
Data Index: 7530989 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.1202. Min Act: -0.1700
Data Index: 8564410 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0889. Min Act: -0.1698
Data Index: 8716573 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0889. Min Act: -0.1700
Data Index: 3987134 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0889. Min Act: -0.1700
Data Index: 3677086 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0889. Min Act: -0.1700
Data Index: 1284406 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0889. Min Act: -0.1698
Data Index: 8198608 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0889. Min Act: -0.1700
Data Index: 7492292 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0889. Min Act: -0.1700
Data Index: 6296773 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0889. Min Act: -0.1686
Data Index: 6189986 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0889. Min Act: -0.1700
Data Index: 2826743 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0577. Min Act: -0.1700
Data Index: 4016672 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3077. Min Range: -5.3077
Max Act: 5.0577. Min Act: -0.1700
Data Index: 2645246 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19