Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4365 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1383. Min Range: -7.1383
Max Act: 7.1383. Min Act: -0.1700
Data Index: 4147245 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1383. Min Range: -7.1383
Max Act: 7.0133. Min Act: -0.1700
Data Index: 5641412 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.9820. Min Act: -0.1700
Data Index: 3939110 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.9195. Min Act: -0.1700
Data Index: 4469835 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.9195. Min Act: -0.1700
Data Index: 2425177 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.9195. Min Act: -0.1700
Data Index: 2105765 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.9195. Min Act: -0.1700
Data Index: 8458467 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.9195. Min Act: -0.1700
Data Index: 4119134 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.8883. Min Act: -0.1700
Data Index: 3208403 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.9195. Min Act: -0.1700
Data Index: 5074117 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.8883. Min Act: -0.1700
Data Index: 8105354 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.8570. Min Act: -0.1700
Data Index: 1967954 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.8570. Min Act: -0.1700
Data Index: 1326512 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.8570. Min Act: -0.1700
Data Index: 7035166 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.8258. Min Act: -0.1700
Data Index: 2480255 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.8570. Min Act: -0.1700
Data Index: 3542394 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.8570. Min Act: -0.1700
Data Index: 1398447 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.8258. Min Act: -0.1700
Data Index: 3126280 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.8258. Min Act: -0.1700
Data Index: 1153808 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1383. Min Range: -7.1383
Max Act: 6.7945. Min Act: -0.1700
Data Index: 2071108 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19