Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5961 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1845. Min Range: -10.1845
Max Act: 10.1845. Min Act: -0.1700
Data Index: 1510559 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1845. Min Range: -10.1845
Max Act: 10.1220. Min Act: -0.1700
Data Index: 4965464 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1845. Min Range: -10.1845
Max Act: 10.1220. Min Act: -0.1700
Data Index: 5866260 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1845. Min Range: -10.1845
Max Act: 10.0595. Min Act: -0.1700
Data Index: 487010 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1845. Min Range: -10.1845
Max Act: 10.0595. Min Act: -0.1700
Data Index: 3225274 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.9345. Min Act: -0.1700
Data Index: 6096378 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.9345. Min Act: -0.1700
Data Index: 8676211 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.8720. Min Act: -0.1700
Data Index: 4079984 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.9345. Min Act: -0.1700
Data Index: 2691198 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.8720. Min Act: -0.1700
Data Index: 7951847 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.8095. Min Act: -0.1700
Data Index: 1390936 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.7470. Min Act: -0.1700
Data Index: 1012961 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.7470. Min Act: -0.1700
Data Index: 2231135 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.7470. Min Act: -0.1700
Data Index: 8462181 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.7470. Min Act: -0.1700
Data Index: 4298494 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.6845. Min Act: -0.1700
Data Index: 6495054 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.6845. Min Act: -0.1700
Data Index: 7076738 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.7470. Min Act: -0.1700
Data Index: 3712856 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.6845. Min Act: -0.1700
Data Index: 2110137 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1845. Min Range: -10.1845
Max Act: 9.6220. Min Act: -0.1700
Data Index: 2346257 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19