Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3167 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.4577. Min Act: -0.1700
Data Index: 3818203 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.4264. Min Act: -0.1700
Data Index: 2281521 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.3952. Min Act: -0.1700
Data Index: 2413415 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.3952. Min Act: -0.1700
Data Index: 3432940 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.3327. Min Act: -0.1700
Data Index: 8223892 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.2702. Min Act: -0.1700
Data Index: 7248245 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.2077. Min Act: -0.1700
Data Index: 8741008 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.1764. Min Act: -0.1700
Data Index: 6269455 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.2077. Min Act: -0.1700
Data Index: 2960936 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.0202. Min Act: -0.1700
Data Index: 608042 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4577. Min Range: -7.4577
Max Act: 6.9889. Min Act: -0.1700
Data Index: 5867609 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4577. Min Range: -7.4577
Max Act: 6.9889. Min Act: -0.1700
Data Index: 4289250 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4577. Min Range: -7.4577
Max Act: 7.0202. Min Act: -0.1700
Data Index: 161176 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4577. Min Range: -7.4577
Max Act: 6.9577. Min Act: -0.1700
Data Index: 7199433 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4577. Min Range: -7.4577
Max Act: 6.9577. Min Act: -0.1700
Data Index: 4174739 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4577. Min Range: -7.4577
Max Act: 6.9264. Min Act: -0.1700
Data Index: 8396227 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4577. Min Range: -7.4577
Max Act: 6.9264. Min Act: -0.1700
Data Index: 7405618 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4577. Min Range: -7.4577
Max Act: 6.9264. Min Act: -0.1700
Data Index: 6950634 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4577. Min Range: -7.4577
Max Act: 6.8952. Min Act: -0.1700
Data Index: 4108929 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4577. Min Range: -7.4577
Max Act: 6.8952. Min Act: -0.1700
Data Index: 5906730 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19