Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2040 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.9633. Min Act: -0.1700
Data Index: 2616709 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.4946. Min Act: -0.1700
Data Index: 2562786 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.5258. Min Act: -0.1700
Data Index: 6822533 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.4633. Min Act: -0.1700
Data Index: 1748859 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.4008. Min Act: -0.1700
Data Index: 5517588 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.4321. Min Act: -0.1700
Data Index: 3671758 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.2758. Min Act: -0.1700
Data Index: 1635064 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.2758. Min Act: -0.1700
Data Index: 8613038 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.3071. Min Act: -0.1700
Data Index: 6730120 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.3071. Min Act: -0.1700
Data Index: 1419016 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.2758. Min Act: -0.1700
Data Index: 4445820 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.2758. Min Act: -0.1700
Data Index: 571900 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.2446. Min Act: -0.1700
Data Index: 2507349 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.2133. Min Act: -0.1700
Data Index: 6009156 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.2133. Min Act: -0.1700
Data Index: 977293 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.1821. Min Act: -0.1700
Data Index: 105805 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.1508. Min Act: -0.1700
Data Index: 4843228 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.1821. Min Act: -0.1700
Data Index: 1540339 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.1821. Min Act: -0.1700
Data Index: 7372348 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9633. Min Range: -5.9633
Max Act: 5.1821. Min Act: -0.1700
Data Index: 8734150 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19