Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4720 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.8596. Min Act: -0.1700
Data Index: 8676435 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.7188. Min Act: -0.1700
Data Index: 6591428 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.6249. Min Act: -0.1700
Data Index: 2240423 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.6249. Min Act: -0.1700
Data Index: 2935546 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.6249. Min Act: -0.1700
Data Index: 5216377 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.6093. Min Act: -0.1700
Data Index: 2053712 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.6093. Min Act: -0.1700
Data Index: 2159765 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.5780. Min Act: -0.1700
Data Index: 904829 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.5623. Min Act: -0.1700
Data Index: 1616001 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.5780. Min Act: -0.1700
Data Index: 2117401 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.5623. Min Act: -0.1700
Data Index: 5984846 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.5154. Min Act: -0.1700
Data Index: 6346389 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.5154. Min Act: -0.1700
Data Index: 5430262 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.4840. Min Act: -0.1700
Data Index: 5451258 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.4997. Min Act: -0.1700
Data Index: 560564 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.4840. Min Act: -0.1700
Data Index: 2127062 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.4684. Min Act: -0.1700
Data Index: 8326791 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.4527. Min Act: -0.1700
Data Index: 7042342 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.4527. Min Act: -0.1700
Data Index: 4882560 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8596. Min Range: -3.8596
Max Act: 3.4684. Min Act: -0.1700
Data Index: 4057380 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19