Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3267 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5241. Min Range: -10.5241
Max Act: 10.5241. Min Act: -0.1700
Data Index: 4125711 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5241. Min Range: -10.5241
Max Act: 10.1491. Min Act: -0.1700
Data Index: 7273600 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5241. Min Range: -10.5241
Max Act: 10.0241. Min Act: -0.1700
Data Index: 7966073 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5241. Min Range: -10.5241
Max Act: 10.0241. Min Act: -0.1700
Data Index: 7728732 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.8366. Min Act: -0.1700
Data Index: 8735934 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.8366. Min Act: -0.1700
Data Index: 179382 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.7741. Min Act: -0.1700
Data Index: 6071902 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.6491. Min Act: -0.1700
Data Index: 1313584 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.6491. Min Act: -0.1700
Data Index: 6256108 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.6491. Min Act: -0.1700
Data Index: 8191648 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.5866. Min Act: -0.1700
Data Index: 1419438 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.5241. Min Act: -0.1700
Data Index: 1070272 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.3991. Min Act: -0.1700
Data Index: 3435906 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.4616. Min Act: -0.1700
Data Index: 5089718 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.5241. Min Act: -0.1700
Data Index: 8788313 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.4616. Min Act: -0.1700
Data Index: 2843847 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.4616. Min Act: -0.1700
Data Index: 8206948 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.3991. Min Act: -0.1700
Data Index: 5201305 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.3991. Min Act: -0.1700
Data Index: 7466179 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5241. Min Range: -10.5241
Max Act: 9.3991. Min Act: -0.1700
Data Index: 3214320 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19