Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.5145. Min Act: -0.1700
Data Index: 5357002 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.5145. Min Act: -0.1700
Data Index: 8075882 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2957. Min Act: -0.1700
Data Index: 546773 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2645. Min Act: -0.1700
Data Index: 5724415 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2020. Min Act: -0.1700
Data Index: 4363320 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2332. Min Act: -0.1700
Data Index: 8080806 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.2332. Min Act: -0.1700
Data Index: 4247393 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1707. Min Act: -0.1700
Data Index: 7409565 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1707. Min Act: -0.1700
Data Index: 439705 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0770. Min Act: -0.1700
Data Index: 5233744 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.1082. Min Act: -0.1700
Data Index: 6488204 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0770. Min Act: -0.1700
Data Index: 5289453 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0457. Min Act: -0.1700
Data Index: 2998511 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0457. Min Act: -0.1700
Data Index: 3548925 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0457. Min Act: -0.1700
Data Index: 6903898 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0145. Min Act: -0.1700
Data Index: 2656201 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5145. Min Range: -6.5145
Max Act: 6.0145. Min Act: -0.1700
Data Index: 3440177 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5145. Min Range: -6.5145
Max Act: 5.9832. Min Act: -0.1700
Data Index: 523744 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5145. Min Range: -6.5145
Max Act: 5.9207. Min Act: -0.1700
Data Index: 8306047 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5145. Min Range: -6.5145
Max Act: 5.9207. Min Act: -0.1700
Data Index: 240581 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19