Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3863 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4368. Min Range: -8.4368
Max Act: 8.4368. Min Act: -0.1700
Data Index: 7927057 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4368. Min Range: -8.4368
Max Act: 7.3118. Min Act: -0.1700
Data Index: 30722 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4368. Min Range: -8.4368
Max Act: 7.2806. Min Act: -0.1700
Data Index: 4153469 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4368. Min Range: -8.4368
Max Act: 7.1868. Min Act: -0.1700
Data Index: 6101545 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4368. Min Range: -8.4368
Max Act: 7.1243. Min Act: -0.1700
Data Index: 3231103 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4368. Min Range: -8.4368
Max Act: 7.0618. Min Act: -0.1700
Data Index: 8371289 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.9681. Min Act: -0.1700
Data Index: 422396 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.9368. Min Act: -0.1700
Data Index: 5169745 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.9056. Min Act: -0.1700
Data Index: 2958462 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.8743. Min Act: -0.1700
Data Index: 1098615 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.8431. Min Act: -0.1700
Data Index: 5513905 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.8118. Min Act: -0.1700
Data Index: 7523694 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.8118. Min Act: -0.1700
Data Index: 395472 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.7493. Min Act: -0.1700
Data Index: 5867875 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.8118. Min Act: -0.1700
Data Index: 3991624 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.7493. Min Act: -0.1700
Data Index: 5867876 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.7493. Min Act: -0.1700
Data Index: 3271195 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.7493. Min Act: -0.1700
Data Index: 2481348 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.7806. Min Act: -0.1700
Data Index: 4653877 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4368. Min Range: -8.4368
Max Act: 6.7181. Min Act: -0.1700
Data Index: 5300762 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19