Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5838 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1794. Min Range: -9.1794
Max Act: 9.1794. Min Act: -0.1700
Data Index: 5697096 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1794. Min Range: -9.1794
Max Act: 9.1794. Min Act: -0.1700
Data Index: 4539226 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.4294. Min Act: -0.1700
Data Index: 8475958 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.4294. Min Act: -0.1700
Data Index: 2451526 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.3044. Min Act: -0.1700
Data Index: 7030535 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.3669. Min Act: -0.1700
Data Index: 4178076 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.2419. Min Act: -0.1700
Data Index: 440841 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.2419. Min Act: -0.1700
Data Index: 732335 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.0856. Min Act: -0.1700
Data Index: 4110865 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.1169. Min Act: -0.1700
Data Index: 2198257 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.0856. Min Act: -0.1700
Data Index: 3394360 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.0544. Min Act: -0.1700
Data Index: 1090033 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.1169. Min Act: -0.1700
Data Index: 4104110 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.0856. Min Act: -0.1700
Data Index: 1090026 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1794. Min Range: -9.1794
Max Act: 8.0231. Min Act: -0.1700
Data Index: 3350110 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1794. Min Range: -9.1794
Max Act: 7.9919. Min Act: -0.1700
Data Index: 3492796 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1794. Min Range: -9.1794
Max Act: 7.9919. Min Act: -0.1700
Data Index: 2249099 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1794. Min Range: -9.1794
Max Act: 7.9919. Min Act: -0.1700
Data Index: 242790 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1794. Min Range: -9.1794
Max Act: 7.9294. Min Act: -0.1700
Data Index: 4410944 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1794. Min Range: -9.1794
Max Act: 7.9606. Min Act: -0.1700
Data Index: 5832803 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19