Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2205 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.8781. Min Act: -0.1700
Data Index: 5373223 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.8781. Min Act: -0.1700
Data Index: 4237236 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.6281. Min Act: -0.1700
Data Index: 7357137 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.5968. Min Act: -0.1700
Data Index: 5962257 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.5968. Min Act: -0.1700
Data Index: 6338492 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.5343. Min Act: -0.1700
Data Index: 5303633 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.5343. Min Act: -0.1700
Data Index: 6186960 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.5031. Min Act: -0.1700
Data Index: 342023 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4406. Min Act: -0.1700
Data Index: 8406299 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4406. Min Act: -0.1700
Data Index: 8018422 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4406. Min Act: -0.1700
Data Index: 8743520 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4406. Min Act: -0.1700
Data Index: 3043572 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4718. Min Act: -0.1700
Data Index: 7999473 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.3781. Min Act: -0.1700
Data Index: 5513278 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.3781. Min Act: -0.1700
Data Index: 6526630 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.4093. Min Act: -0.1700
Data Index: 5551111 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.3468. Min Act: -0.1700
Data Index: 7675131 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.2843. Min Act: -0.1700
Data Index: 1971892 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.2531. Min Act: -0.1700
Data Index: 3115359 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8781. Min Range: -6.8781
Max Act: 6.2843. Min Act: -0.1700
Data Index: 8247082 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19