Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3400 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3658. Min Range: -8.3658
Max Act: 8.3658. Min Act: -0.1700
Data Index: 1338058 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3658. Min Range: -8.3658
Max Act: 8.0221. Min Act: -0.1700
Data Index: 428221 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.9908. Min Act: -0.1700
Data Index: 6868157 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.9908. Min Act: -0.1700
Data Index: 6164826 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.9283. Min Act: -0.1700
Data Index: 1682375 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.8658. Min Act: -0.1700
Data Index: 7282376 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.8971. Min Act: -0.1700
Data Index: 385751 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.8971. Min Act: -0.1700
Data Index: 6928581 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.8658. Min Act: -0.1700
Data Index: 4970378 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.8658. Min Act: -0.1700
Data Index: 6870310 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.8033. Min Act: -0.1700
Data Index: 3660985 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.6471. Min Act: -0.1700
Data Index: 6118456 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.6783. Min Act: -0.1700
Data Index: 2455153 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.6471. Min Act: -0.1700
Data Index: 5000680 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.6783. Min Act: -0.1700
Data Index: 2806785 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.6158. Min Act: -0.1700
Data Index: 7612250 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.6158. Min Act: -0.1700
Data Index: 4112534 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.6158. Min Act: -0.1700
Data Index: 3183514 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.5846. Min Act: -0.1700
Data Index: 8480566 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3658. Min Range: -8.3658
Max Act: 7.6158. Min Act: -0.1700
Data Index: 4448870 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19