Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5881 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.5795. Min Act: -0.1700
Data Index: 1121376 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.4232. Min Act: -0.1700
Data Index: 5431770 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.4545. Min Act: -0.1700
Data Index: 5770929 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.2670. Min Act: -0.1700
Data Index: 4118791 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.2357. Min Act: -0.1700
Data Index: 42576 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.1107. Min Act: -0.1700
Data Index: 7896886 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.0482. Min Act: -0.1700
Data Index: 2882561 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.0482. Min Act: -0.1700
Data Index: 2414473 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.0795. Min Act: -0.1700
Data Index: 1817994 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.0170. Min Act: -0.1700
Data Index: 1889326 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5795. Min Range: -5.5795
Max Act: 5.0170. Min Act: -0.1700
Data Index: 8071478 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5795. Min Range: -5.5795
Max Act: 4.9545. Min Act: -0.1700
Data Index: 3846421 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5795. Min Range: -5.5795
Max Act: 4.9857. Min Act: -0.1700
Data Index: 6372444 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5795. Min Range: -5.5795
Max Act: 4.9232. Min Act: -0.1700
Data Index: 6882149 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5795. Min Range: -5.5795
Max Act: 4.9232. Min Act: -0.1700
Data Index: 6947582 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5795. Min Range: -5.5795
Max Act: 4.8920. Min Act: -0.1700
Data Index: 2134322 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5795. Min Range: -5.5795
Max Act: 4.8607. Min Act: -0.1700
Data Index: 8759646 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5795. Min Range: -5.5795
Max Act: 4.8295. Min Act: -0.1700
Data Index: 4969611 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5795. Min Range: -5.5795
Max Act: 4.8295. Min Act: -0.1700
Data Index: 6148090 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5795. Min Range: -5.5795
Max Act: 4.8295. Min Act: -0.1700
Data Index: 1940354 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19