Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1366 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2666. Min Range: -7.2666
Max Act: 7.2666. Min Act: -0.1700
Data Index: 7741421 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.6103. Min Act: -0.1700
Data Index: 5746203 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.6416. Min Act: -0.1700
Data Index: 2993213 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.6103. Min Act: -0.1700
Data Index: 7965015 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.6103. Min Act: -0.1700
Data Index: 2514180 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.6103. Min Act: -0.1700
Data Index: 7414198 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.5478. Min Act: -0.1700
Data Index: 4895497 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.5478. Min Act: -0.1700
Data Index: 6555564 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.5166. Min Act: -0.1700
Data Index: 4989246 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.4853. Min Act: -0.1700
Data Index: 8628486 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.4541. Min Act: -0.1700
Data Index: 445499 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.4541. Min Act: -0.1700
Data Index: 5381118 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.4541. Min Act: -0.1700
Data Index: 8616478 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.4541. Min Act: -0.1700
Data Index: 573795 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.4541. Min Act: -0.1700
Data Index: 7878463 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.4228. Min Act: -0.1700
Data Index: 1481355 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.4541. Min Act: -0.1700
Data Index: 2441140 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.4228. Min Act: -0.1700
Data Index: 6955317 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.4228. Min Act: -0.1700
Data Index: 2653698 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2666. Min Range: -7.2666
Max Act: 6.3916. Min Act: -0.1700
Data Index: 588873 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19