Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.3612. Min Act: -0.1700
Data Index: 223712 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.2827. Min Act: -0.1700
Data Index: 7570523 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.2513. Min Act: -0.1700
Data Index: 8394217 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.2513. Min Act: -0.1700
Data Index: 4356386 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.2513. Min Act: -0.1700
Data Index: 6110598 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.2513. Min Act: -0.1700
Data Index: 5511207 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.2356. Min Act: -0.1700
Data Index: 3756631 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.2356. Min Act: -0.1700
Data Index: 4232885 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.2199. Min Act: -0.1700
Data Index: 1179757 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.2356. Min Act: -0.1700
Data Index: 6033665 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.1884. Min Act: -0.1700
Data Index: 8457011 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.2041. Min Act: -0.1700
Data Index: 493968 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.1884. Min Act: -0.1700
Data Index: 8082094 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.1884. Min Act: -0.1700
Data Index: 5116195 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.1884. Min Act: -0.1700
Data Index: 8737213 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.1884. Min Act: -0.1700
Data Index: 8064094 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.1727. Min Act: -0.1700
Data Index: 3599766 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.1727. Min Act: -0.1700
Data Index: 2005979 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.1727. Min Act: -0.1700
Data Index: 8241750 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3612. Min Range: -3.3612
Max Act: 3.1412. Min Act: -0.1700
Data Index: 1294 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19