Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3556 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.8860. Min Act: -0.1700
Data Index: 8627931 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.5735. Min Act: -0.1700
Data Index: 6266448 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.4173. Min Act: -0.1700
Data Index: 5135851 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.3548. Min Act: -0.1700
Data Index: 8084775 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.2923. Min Act: -0.1700
Data Index: 4675677 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.2610. Min Act: -0.1700
Data Index: 6402723 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.2298. Min Act: -0.1700
Data Index: 1547202 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.2298. Min Act: -0.1700
Data Index: 3401632 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.1985. Min Act: -0.1700
Data Index: 5003090 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.1047. Min Act: -0.1700
Data Index: 6865351 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.1047. Min Act: -0.1700
Data Index: 5229297 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.0422. Min Act: -0.1700
Data Index: 8412312 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.0422. Min Act: -0.1700
Data Index: 5346890 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.0422. Min Act: -0.1700
Data Index: 6262526 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.0422. Min Act: -0.1700
Data Index: 408389 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.0735. Min Act: -0.1700
Data Index: 4323008 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.0422. Min Act: -0.1700
Data Index: 1819484 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8860. Min Range: -4.8860
Max Act: 3.9797. Min Act: -0.1700
Data Index: 6850765 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.0110. Min Act: -0.1700
Data Index: 1426555 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8860. Min Range: -4.8860
Max Act: 4.0110. Min Act: -0.1700
Data Index: 8581190 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19