Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3973 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5552. Min Range: -8.5552
Max Act: 8.5552. Min Act: -0.1700
Data Index: 7350567 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5552. Min Range: -8.5552
Max Act: 8.5552. Min Act: -0.1700
Data Index: 6078318 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5552. Min Range: -8.5552
Max Act: 8.2427. Min Act: -0.1700
Data Index: 8412069 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5552. Min Range: -8.5552
Max Act: 8.2427. Min Act: -0.1700
Data Index: 2807438 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5552. Min Range: -8.5552
Max Act: 8.0864. Min Act: -0.1700
Data Index: 2568199 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.8989. Min Act: -0.1700
Data Index: 4954718 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.8677. Min Act: -0.1700
Data Index: 1195028 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.8677. Min Act: -0.1700
Data Index: 6542108 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.8677. Min Act: -0.1700
Data Index: 687730 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.8677. Min Act: -0.1700
Data Index: 8202300 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.8052. Min Act: -0.1700
Data Index: 4860297 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.7739. Min Act: -0.1700
Data Index: 7659099 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.7739. Min Act: -0.1700
Data Index: 2928832 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.7427. Min Act: -0.1700
Data Index: 5742114 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.7427. Min Act: -0.1700
Data Index: 6035205 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.6802. Min Act: -0.1700
Data Index: 7885187 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.6802. Min Act: -0.1700
Data Index: 3476667 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.6489. Min Act: -0.1700
Data Index: 8806421 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.5864. Min Act: -0.1700
Data Index: 5145937 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5552. Min Range: -8.5552
Max Act: 7.6177. Min Act: -0.1700
Data Index: 5733526 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19