Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2420 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5389. Min Range: -8.5389
Max Act: 8.5389. Min Act: -0.1700
Data Index: 8407041 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.8514. Min Act: -0.1700
Data Index: 6332477 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.7264. Min Act: -0.1700
Data Index: 384243 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.6951. Min Act: -0.1700
Data Index: 333706 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.5701. Min Act: -0.1700
Data Index: 5948145 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.5076. Min Act: -0.1700
Data Index: 4588810 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.4764. Min Act: -0.1700
Data Index: 7336977 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.4764. Min Act: -0.1700
Data Index: 3495555 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.4764. Min Act: -0.1700
Data Index: 4937429 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.4451. Min Act: -0.1700
Data Index: 1441474 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.4451. Min Act: -0.1700
Data Index: 6859349 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.3514. Min Act: -0.1700
Data Index: 7224196 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.3514. Min Act: -0.1700
Data Index: 2447110 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.3201. Min Act: -0.1700
Data Index: 7384179 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.2889. Min Act: -0.1700
Data Index: 4622652 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.2264. Min Act: -0.1700
Data Index: 4276411 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.2576. Min Act: -0.1700
Data Index: 3124997 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.2576. Min Act: -0.1700
Data Index: 5676038 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.2264. Min Act: -0.1700
Data Index: 281356 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5389. Min Range: -8.5389
Max Act: 7.1951. Min Act: -0.1700
Data Index: 4989548 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19