Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3215 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.5250. Min Act: -0.1700
Data Index: 4263864 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.5250. Min Act: -0.1700
Data Index: 7639847 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.4937. Min Act: -0.1700
Data Index: 4652538 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.3687. Min Act: -0.1700
Data Index: 6111233 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.4000. Min Act: -0.1700
Data Index: 1035762 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.4000. Min Act: -0.1700
Data Index: 2874905 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.3687. Min Act: -0.1700
Data Index: 8119978 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.3375. Min Act: -0.1700
Data Index: 2556217 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.3062. Min Act: -0.1700
Data Index: 4566353 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.3062. Min Act: -0.1700
Data Index: 4379311 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.3062. Min Act: -0.1700
Data Index: 4650959 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.2750. Min Act: -0.1700
Data Index: 6933243 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.2437. Min Act: -0.1700
Data Index: 6761586 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.2750. Min Act: -0.1700
Data Index: 6408233 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.2750. Min Act: -0.1700
Data Index: 3977780 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.3375. Min Act: -0.1700
Data Index: 4522029 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.3062. Min Act: -0.1700
Data Index: 7378634 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.2437. Min Act: -0.1700
Data Index: 335040 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.2750. Min Act: -0.1700
Data Index: 6389399 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5250. Min Range: -7.5250
Max Act: 7.2437. Min Act: -0.1700
Data Index: 2556236 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19