Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 956 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.2691. Min Act: -0.1700
Data Index: 3576412 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.1128. Min Act: -0.1700
Data Index: 6018241 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0816. Min Act: -0.1700
Data Index: 4203096 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0816. Min Act: -0.1700
Data Index: 4556148 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0816. Min Act: -0.1700
Data Index: 7279910 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0503. Min Act: -0.1700
Data Index: 5632931 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0503. Min Act: -0.1700
Data Index: 2164746 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0503. Min Act: -0.1700
Data Index: 973022 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0191. Min Act: -0.1700
Data Index: 4791165 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0816. Min Act: -0.1700
Data Index: 5098483 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0191. Min Act: -0.1700
Data Index: 4424386 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0503. Min Act: -0.1700
Data Index: 2004386 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0191. Min Act: -0.1700
Data Index: 3818644 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2691. Min Range: -4.2691
Max Act: 3.9878. Min Act: -0.1700
Data Index: 8382811 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2691. Min Range: -4.2691
Max Act: 3.9878. Min Act: -0.1700
Data Index: 7444658 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2691. Min Range: -4.2691
Max Act: 4.0191. Min Act: -0.1700
Data Index: 6847923 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2691. Min Range: -4.2691
Max Act: 3.9565. Min Act: -0.1700
Data Index: 3507441 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2691. Min Range: -4.2691
Max Act: 3.9565. Min Act: -0.1700
Data Index: 6100577 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2691. Min Range: -4.2691
Max Act: 3.9253. Min Act: -0.1700
Data Index: 4821628 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2691. Min Range: -4.2691
Max Act: 3.9565. Min Act: -0.1700
Data Index: 7939752 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19