Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.8263. Min Act: -0.1700
Data Index: 8234123 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.7013. Min Act: -0.1700
Data Index: 1064614 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.5763. Min Act: -0.1700
Data Index: 1584223 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.5451. Min Act: -0.1700
Data Index: 8671398 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.5138. Min Act: -0.1700
Data Index: 6701237 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.4513. Min Act: -0.1700
Data Index: 2621523 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.5138. Min Act: -0.1700
Data Index: 8054013 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.4826. Min Act: -0.1700
Data Index: 106855 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.4513. Min Act: -0.1700
Data Index: 7333114 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.4826. Min Act: -0.1700
Data Index: 8745428 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.4201. Min Act: -0.1700
Data Index: 7352582 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.4201. Min Act: -0.1700
Data Index: 8648563 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.4513. Min Act: -0.1700
Data Index: 694072 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.3888. Min Act: -0.1700
Data Index: 6369612 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.3888. Min Act: -0.1700
Data Index: 4568790 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.3888. Min Act: -0.1700
Data Index: 6083733 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.3888. Min Act: -0.1700
Data Index: 5284271 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.3888. Min Act: -0.1700
Data Index: 3623679 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.3576. Min Act: -0.1700
Data Index: 2292923 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8263. Min Range: -6.8263
Max Act: 6.3576. Min Act: -0.1700
Data Index: 6098493 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #19