Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1555 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.6240. Min Act: -0.1700
Data Index: 347174 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.5302. Min Act: -0.1700
Data Index: 4071342 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.5302. Min Act: -0.1700
Data Index: 5380078 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.4677. Min Act: -0.1700
Data Index: 1034596 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.4052. Min Act: -0.1700
Data Index: 4581661 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.2177. Min Act: -0.1700
Data Index: 7282125 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.1865. Min Act: -0.1700
Data Index: 7869570 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.2177. Min Act: -0.1700
Data Index: 1684640 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.0615. Min Act: -0.1700
Data Index: 3180001 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.0302. Min Act: -0.1700
Data Index: 1578798 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6240. Min Range: -5.6240
Max Act: 5.0302. Min Act: -0.1700
Data Index: 1408829 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6240. Min Range: -5.6240
Max Act: 4.9990. Min Act: -0.1700
Data Index: 1264906 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6240. Min Range: -5.6240
Max Act: 4.9990. Min Act: -0.1700
Data Index: 4598369 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6240. Min Range: -5.6240
Max Act: 4.9990. Min Act: -0.1700
Data Index: 2439277 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6240. Min Range: -5.6240
Max Act: 4.9677. Min Act: -0.1700
Data Index: 1175717 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6240. Min Range: -5.6240
Max Act: 4.9677. Min Act: -0.1700
Data Index: 735835 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6240. Min Range: -5.6240
Max Act: 4.9365. Min Act: -0.1700
Data Index: 3656778 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6240. Min Range: -5.6240
Max Act: 4.9365. Min Act: -0.1700
Data Index: 1745681 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6240. Min Range: -5.6240
Max Act: 4.9365. Min Act: -0.1700
Data Index: 7639562 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6240. Min Range: -5.6240
Max Act: 4.9365. Min Act: -0.1700
Data Index: 5185526 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19