Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3897 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0573. Min Range: -5.0573
Max Act: 5.0573. Min Act: -0.1700
Data Index: 4870943 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.9948. Min Act: -0.1700
Data Index: 3237951 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.9636. Min Act: -0.1700
Data Index: 7578965 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.8698. Min Act: -0.1700
Data Index: 1033172 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.9011. Min Act: -0.1700
Data Index: 4870945 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.7448. Min Act: -0.1700
Data Index: 690117 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.5573. Min Act: -0.1700
Data Index: 2285158 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.5573. Min Act: -0.1700
Data Index: 6876112 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.5261. Min Act: -0.1700
Data Index: 2184704 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.5573. Min Act: -0.1700
Data Index: 2238497 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.5261. Min Act: -0.1700
Data Index: 1658174 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.5261. Min Act: -0.1700
Data Index: 8484166 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.5573. Min Act: -0.1700
Data Index: 2409934 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.4948. Min Act: -0.1700
Data Index: 3895391 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.4323. Min Act: -0.1700
Data Index: 6574634 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.4323. Min Act: -0.1700
Data Index: 4136315 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.4011. Min Act: -0.1700
Data Index: 3112037 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.4011. Min Act: -0.1700
Data Index: 7962752 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.4011. Min Act: -0.1700
Data Index: 3097732 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0573. Min Range: -5.0573
Max Act: 4.3698. Min Act: -0.1700
Data Index: 5809791 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19