Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3634 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.4564. Min Act: -0.1700
Data Index: 8046844 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3627. Min Act: -0.1700
Data Index: 3241192 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3939. Min Act: -0.1700
Data Index: 8436578 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3627. Min Act: -0.1700
Data Index: 795300 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3314. Min Act: -0.1700
Data Index: 1733277 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3314. Min Act: -0.1700
Data Index: 1904056 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3002. Min Act: -0.1700
Data Index: 1647770 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3002. Min Act: -0.1700
Data Index: 3047672 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3002. Min Act: -0.1700
Data Index: 5633245 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3002. Min Act: -0.1700
Data Index: 7329410 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3002. Min Act: -0.1700
Data Index: 4897702 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.3002. Min Act: -0.1700
Data Index: 2418113 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.2689. Min Act: -0.1700
Data Index: 5836798 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.2689. Min Act: -0.1700
Data Index: 8034386 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.2689. Min Act: -0.1700
Data Index: 2652006 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.2689. Min Act: -0.1700
Data Index: 7956831 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.2689. Min Act: -0.1700
Data Index: 3211866 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.2689. Min Act: -0.1700
Data Index: 1110598 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.2689. Min Act: -0.1700
Data Index: 6163639 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4564. Min Range: -5.4564
Max Act: 5.2377. Min Act: -0.1700
Data Index: 4897703 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19