Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4355 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0651. Min Range: -6.0651
Max Act: 6.0651. Min Act: -0.1700
Data Index: 5857900 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0651. Min Range: -6.0651
Max Act: 6.0026. Min Act: -0.1700
Data Index: 3946361 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.7213. Min Act: -0.1700
Data Index: 2858458 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.5651. Min Act: -0.1700
Data Index: 5565749 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.5651. Min Act: -0.1700
Data Index: 60043 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.4401. Min Act: -0.1700
Data Index: 3558949 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.4088. Min Act: -0.1700
Data Index: 6059490 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.3463. Min Act: -0.1700
Data Index: 1740088 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.3151. Min Act: -0.1700
Data Index: 7757382 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.3463. Min Act: -0.1700
Data Index: 2082086 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.2526. Min Act: -0.1700
Data Index: 8049495 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.2526. Min Act: -0.1700
Data Index: 4376599 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.2526. Min Act: -0.1700
Data Index: 2808214 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.2526. Min Act: -0.1700
Data Index: 6184227 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.2526. Min Act: -0.1700
Data Index: 5258749 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.2526. Min Act: -0.1700
Data Index: 7657804 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.2213. Min Act: -0.1700
Data Index: 2665167 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.1901. Min Act: -0.1700
Data Index: 7218429 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.1901. Min Act: -0.1700
Data Index: 4019153 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0651. Min Range: -6.0651
Max Act: 5.1588. Min Act: -0.1700
Data Index: 1797840 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19