Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2952 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9668. Min Range: -9.9668
Max Act: 9.9668. Min Act: -0.1700
Data Index: 8756361 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9668. Min Range: -9.9668
Max Act: 9.8418. Min Act: -0.1700
Data Index: 8414778 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9668. Min Range: -9.9668
Max Act: 9.8418. Min Act: -0.1700
Data Index: 2004432 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9668. Min Range: -9.9668
Max Act: 9.5918. Min Act: -0.1700
Data Index: 2154565 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9668. Min Range: -9.9668
Max Act: 9.2168. Min Act: -0.1700
Data Index: 5596672 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.7168. Min Act: -0.1700
Data Index: 8062127 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.4668. Min Act: -0.1700
Data Index: 4817003 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.3731. Min Act: -0.1700
Data Index: 3569718 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.3418. Min Act: -0.1700
Data Index: 8374360 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.3106. Min Act: -0.1700
Data Index: 8335021 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.3106. Min Act: -0.1700
Data Index: 3832496 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.3106. Min Act: -0.1700
Data Index: 8700510 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.2793. Min Act: -0.1700
Data Index: 7457967 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.2168. Min Act: -0.1700
Data Index: 8540610 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.2481. Min Act: -0.1700
Data Index: 6668949 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.2481. Min Act: -0.1700
Data Index: 8364774 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.2481. Min Act: -0.1700
Data Index: 5041540 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.2168. Min Act: -0.1700
Data Index: 6489540 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.1856. Min Act: -0.1700
Data Index: 6085220 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9668. Min Range: -9.9668
Max Act: 8.1231. Min Act: -0.1700
Data Index: 2779977 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19