Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2074 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.4025. Min Act: -0.1700
Data Index: 1920385 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.4025. Min Act: -0.1700
Data Index: 6724203 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.2462. Min Act: -0.1700
Data Index: 7500653 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.2150. Min Act: -0.1700
Data Index: 2513593 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.2150. Min Act: -0.1700
Data Index: 6152292 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.1837. Min Act: -0.1700
Data Index: 3234701 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.1212. Min Act: -0.1700
Data Index: 1612291 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0900. Min Act: -0.1700
Data Index: 5995891 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0900. Min Act: -0.1700
Data Index: 4582354 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0587. Min Act: -0.1700
Data Index: 6395698 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 7556407 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 7973166 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 7316949 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 294630 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4025. Min Range: -5.4025
Max Act: 5.0275. Min Act: -0.1700
Data Index: 2406585 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 3440858 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 3201762 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9650. Min Act: -0.1700
Data Index: 3314315 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 2845366 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4025. Min Range: -5.4025
Max Act: 4.9962. Min Act: -0.1700
Data Index: 5664276 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19