Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3072 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.7220. Min Act: -0.1700
Data Index: 3654209 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.5345. Min Act: -0.1700
Data Index: 8657736 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.5032. Min Act: -0.1700
Data Index: 5022484 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.5032. Min Act: -0.1700
Data Index: 1045306 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.4720. Min Act: -0.1700
Data Index: 50237 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.4407. Min Act: -0.1700
Data Index: 8781798 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.4095. Min Act: -0.1700
Data Index: 8593404 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3782. Min Act: -0.1700
Data Index: 8445969 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3782. Min Act: -0.1700
Data Index: 5509301 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3470. Min Act: -0.1700
Data Index: 659643 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3470. Min Act: -0.1700
Data Index: 8279373 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3470. Min Act: -0.1700
Data Index: 1251812 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3470. Min Act: -0.1700
Data Index: 1922074 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3782. Min Act: -0.1700
Data Index: 2111994 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3470. Min Act: -0.1700
Data Index: 2098681 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3470. Min Act: -0.1700
Data Index: 5331632 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3470. Min Act: -0.1700
Data Index: 8445957 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3470. Min Act: -0.1700
Data Index: 6295302 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3470. Min Act: -0.1700
Data Index: 3923817 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7220. Min Range: -4.7220
Max Act: 4.3157. Min Act: -0.1700
Data Index: 2911895 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #19