Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5246 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.6824. Min Act: -0.1700
Data Index: 7721084 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.6824. Min Act: -0.1700
Data Index: 8451163 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.6199. Min Act: -0.1700
Data Index: 6904649 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.5574. Min Act: -0.1700
Data Index: 249194 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.5574. Min Act: -0.1700
Data Index: 4911277 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.4949. Min Act: -0.1700
Data Index: 6196500 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.4949. Min Act: -0.1700
Data Index: 5232446 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.4324. Min Act: -0.1700
Data Index: 3059112 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.4949. Min Act: -0.1700
Data Index: 2745742 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3699. Min Act: -0.1700
Data Index: 7365457 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3699. Min Act: -0.1700
Data Index: 5420218 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3699. Min Act: -0.1700
Data Index: 7031802 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3699. Min Act: -0.1700
Data Index: 427838 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3699. Min Act: -0.1700
Data Index: 6359070 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3699. Min Act: -0.1700
Data Index: 5450337 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3074. Min Act: -0.1700
Data Index: 2867541 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3074. Min Act: -0.1700
Data Index: 6231182 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3074. Min Act: -0.1700
Data Index: 6494198 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3074. Min Act: -0.1700
Data Index: 222691 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6824. Min Range: -8.6824
Max Act: 8.3074. Min Act: -0.1700
Data Index: 3056477 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19