Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4199 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.7422. Min Act: -0.1700
Data Index: 3099986 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.6797. Min Act: -0.1700
Data Index: 291491 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.6172. Min Act: -0.1700
Data Index: 471055 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.5860. Min Act: -0.1700
Data Index: 11654 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.5235. Min Act: -0.1700
Data Index: 2664791 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4922. Min Act: -0.1700
Data Index: 4583608 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4922. Min Act: -0.1700
Data Index: 372066 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4922. Min Act: -0.1700
Data Index: 6061515 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4610. Min Act: -0.1700
Data Index: 940016 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4922. Min Act: -0.1700
Data Index: 6911704 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4922. Min Act: -0.1700
Data Index: 4199471 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4610. Min Act: -0.1700
Data Index: 1349210 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4297. Min Act: -0.1700
Data Index: 3752477 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4610. Min Act: -0.1700
Data Index: 3730868 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4297. Min Act: -0.1700
Data Index: 6452902 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4297. Min Act: -0.1700
Data Index: 337797 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.3985. Min Act: -0.1700
Data Index: 7721539 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.3985. Min Act: -0.1700
Data Index: 3372628 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.4297. Min Act: -0.1700
Data Index: 8190160 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7422. Min Range: -4.7422
Max Act: 4.3985. Min Act: -0.1700
Data Index: 6097414 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19