Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3220 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.9622. Min Act: -0.1700
Data Index: 72014 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.6810. Min Act: -0.1700
Data Index: 8778239 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.4310. Min Act: -0.1700
Data Index: 631880 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.1810. Min Act: -0.1700
Data Index: 5553776 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.1497. Min Act: -0.1700
Data Index: 2977126 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.0560. Min Act: -0.1700
Data Index: 8822416 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.0247. Min Act: -0.1700
Data Index: 7845342 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9935. Min Act: -0.1700
Data Index: 5767923 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9622. Min Range: -7.9622
Max Act: 7.0247. Min Act: -0.1700
Data Index: 3947935 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9935. Min Act: -0.1700
Data Index: 6244176 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9622. Min Act: -0.1700
Data Index: 3639125 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9935. Min Act: -0.1700
Data Index: 7162531 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9935. Min Act: -0.1700
Data Index: 8050848 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9622. Min Act: -0.1700
Data Index: 3725048 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9310. Min Act: -0.1700
Data Index: 564337 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9622. Min Act: -0.1700
Data Index: 524119 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9622. Min Act: -0.1700
Data Index: 5647222 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9310. Min Act: -0.1700
Data Index: 2893182 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9310. Min Act: -0.1700
Data Index: 1285800 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9622. Min Range: -7.9622
Max Act: 6.9310. Min Act: -0.1700
Data Index: 5664094 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19