Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 426 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7020. Min Range: -8.7020
Max Act: 8.7020. Min Act: -0.1700
Data Index: 3994484 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.9208. Min Act: -0.1700
Data Index: 3525288 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.8583. Min Act: -0.1700
Data Index: 2249453 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.7645. Min Act: -0.1700
Data Index: 3260843 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.6395. Min Act: -0.1700
Data Index: 5771663 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.6708. Min Act: -0.1700
Data Index: 1753322 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.6395. Min Act: -0.1700
Data Index: 1766313 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.6395. Min Act: -0.1700
Data Index: 7566284 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.6395. Min Act: -0.1700
Data Index: 8563435 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.5458. Min Act: -0.1700
Data Index: 3052747 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.4833. Min Act: -0.1700
Data Index: 3177772 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.3895. Min Act: -0.1700
Data Index: 4193797 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.4208. Min Act: -0.1700
Data Index: 8664254 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.3270. Min Act: -0.1700
Data Index: 6652589 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.2958. Min Act: -0.1700
Data Index: 5607969 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.2958. Min Act: -0.1700
Data Index: 1426299 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.2958. Min Act: -0.1700
Data Index: 3290974 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.2645. Min Act: -0.1700
Data Index: 6084284 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.2958. Min Act: -0.1700
Data Index: 618445 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7020. Min Range: -8.7020
Max Act: 7.2645. Min Act: -0.1700
Data Index: 6230063 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19