Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3233 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8157. Min Range: -9.8157
Max Act: 9.8157. Min Act: -0.1700
Data Index: 4123522 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8157. Min Range: -9.8157
Max Act: 9.4407. Min Act: -0.1700
Data Index: 8147812 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8157. Min Range: -9.8157
Max Act: 9.1907. Min Act: -0.1700
Data Index: 4064088 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.8469. Min Act: -0.1700
Data Index: 2991229 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.8157. Min Act: -0.1700
Data Index: 7066756 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.7532. Min Act: -0.1700
Data Index: 3190399 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.6907. Min Act: -0.1700
Data Index: 6986592 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.6594. Min Act: -0.1700
Data Index: 7953173 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.6282. Min Act: -0.1700
Data Index: 5836534 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.6282. Min Act: -0.1700
Data Index: 8371951 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.6282. Min Act: -0.1700
Data Index: 7034856 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.5969. Min Act: -0.1700
Data Index: 6279073 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.6282. Min Act: -0.1700
Data Index: 5909268 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.5657. Min Act: -0.1700
Data Index: 2210455 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.6282. Min Act: -0.1700
Data Index: 6801957 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.5969. Min Act: -0.1700
Data Index: 7034855 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.5657. Min Act: -0.1700
Data Index: 339528 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.5657. Min Act: -0.1700
Data Index: 3120979 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.5657. Min Act: -0.1700
Data Index: 6279074 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8157. Min Range: -9.8157
Max Act: 7.5657. Min Act: -0.1700
Data Index: 3262417 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #19