Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.6194. Min Act: -0.1700
Data Index: 3262871 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.4944. Min Act: -0.1700
Data Index: 996632 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.4632. Min Act: -0.1700
Data Index: 2338816 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.4944. Min Act: -0.1700
Data Index: 1349389 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.4632. Min Act: -0.1700
Data Index: 2902399 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.4944. Min Act: -0.1700
Data Index: 4994904 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3594162 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3937813 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.4319. Min Act: -0.1700
Data Index: 2163792 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.4319. Min Act: -0.1700
Data Index: 3501105 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.4007. Min Act: -0.1700
Data Index: 113752 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.3694. Min Act: -0.1700
Data Index: 3774061 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.3694. Min Act: -0.1700
Data Index: 8447119 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.3694. Min Act: -0.1700
Data Index: 4074219 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.3382. Min Act: -0.1700
Data Index: 5894448 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.3382. Min Act: -0.1700
Data Index: 3614282 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.3382. Min Act: -0.1700
Data Index: 6092035 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.3694. Min Act: -0.1700
Data Index: 6817166 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.3382. Min Act: -0.1700
Data Index: 3354685 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6194. Min Range: -5.6194
Max Act: 5.3069. Min Act: -0.1700
Data Index: 7919245 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19