Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2809 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.2974. Min Act: -0.1700
Data Index: 3134217 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.2662. Min Act: -0.1700
Data Index: 7739314 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.2662. Min Act: -0.1700
Data Index: 7231831 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.2349. Min Act: -0.1700
Data Index: 4974790 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.1412. Min Act: -0.1700
Data Index: 1210497 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2974. Min Range: -6.2974
Max Act: 6.0474. Min Act: -0.1700
Data Index: 197237 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9849. Min Act: -0.1700
Data Index: 6834738 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9537. Min Act: -0.1700
Data Index: 1158908 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9537. Min Act: -0.1700
Data Index: 4817142 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9537. Min Act: -0.1700
Data Index: 4373544 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9537. Min Act: -0.1700
Data Index: 7180509 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9537. Min Act: -0.1700
Data Index: 8117028 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9537. Min Act: -0.1700
Data Index: 556795 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 993147 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.9224. Min Act: -0.1700
Data Index: 6500892 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.8912. Min Act: -0.1700
Data Index: 2302271 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.8912. Min Act: -0.1700
Data Index: 2952473 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.8599. Min Act: -0.1700
Data Index: 978283 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.8599. Min Act: -0.1700
Data Index: 2302267 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2974. Min Range: -6.2974
Max Act: 5.8287. Min Act: -0.1700
Data Index: 3979813 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19