Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3928 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.6735. Min Act: -0.1700
Data Index: 8571601 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.6110. Min Act: -0.1700
Data Index: 5821576 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.6422. Min Act: -0.1700
Data Index: 8593685 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.5172. Min Act: -0.1700
Data Index: 654051 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.4547. Min Act: -0.1700
Data Index: 472679 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.3922. Min Act: -0.1700
Data Index: 1785534 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.4235. Min Act: -0.1700
Data Index: 4273807 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.3922. Min Act: -0.1700
Data Index: 2935639 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.3610. Min Act: -0.1700
Data Index: 3849523 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.2985. Min Act: -0.1700
Data Index: 5802840 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.2985. Min Act: -0.1700
Data Index: 6618080 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.2985. Min Act: -0.1700
Data Index: 8335347 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.2672. Min Act: -0.1700
Data Index: 5247262 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.2672. Min Act: -0.1700
Data Index: 8256345 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.2672. Min Act: -0.1700
Data Index: 7911815 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.2360. Min Act: -0.1700
Data Index: 7379651 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.2047. Min Act: -0.1700
Data Index: 765142 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.2047. Min Act: -0.1700
Data Index: 8441122 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.1735. Min Act: -0.1700
Data Index: 924872 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6735. Min Range: -6.6735
Max Act: 6.2047. Min Act: -0.1700
Data Index: 100273 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19