Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2603 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0780. Min Range: -7.0780
Max Act: 7.0780. Min Act: -0.1700
Data Index: 679380 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0780. Min Range: -7.0780
Max Act: 7.0155. Min Act: -0.1700
Data Index: 5120563 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.9217. Min Act: -0.1700
Data Index: 4622278 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.8905. Min Act: -0.1700
Data Index: 5528426 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.8592. Min Act: -0.1700
Data Index: 6506799 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.8592. Min Act: -0.1700
Data Index: 3148235 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.8280. Min Act: -0.1700
Data Index: 8206608 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.8280. Min Act: -0.1700
Data Index: 7687711 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.8280. Min Act: -0.1700
Data Index: 4397361 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.7967. Min Act: -0.1700
Data Index: 8493328 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.8280. Min Act: -0.1700
Data Index: 3803939 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.7967. Min Act: -0.1700
Data Index: 2964424 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.7967. Min Act: -0.1700
Data Index: 5453854 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.7655. Min Act: -0.1700
Data Index: 4663323 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.7655. Min Act: -0.1700
Data Index: 6265760 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.7967. Min Act: -0.1700
Data Index: 7687710 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.7655. Min Act: -0.1700
Data Index: 3599227 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.7655. Min Act: -0.1700
Data Index: 3248450 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.7655. Min Act: -0.1700
Data Index: 7848419 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0780. Min Range: -7.0780
Max Act: 6.7030. Min Act: -0.1700
Data Index: 6352068 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19