Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.8666. Min Act: -0.1700
Data Index: 2048882 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.5541. Min Act: -0.1700
Data Index: 5758286 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.5229. Min Act: -0.1700
Data Index: 242399 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.4916. Min Act: -0.1700
Data Index: 3049371 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.4604. Min Act: -0.1700
Data Index: 781626 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.4916. Min Act: -0.1700
Data Index: 4765329 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.4916. Min Act: -0.1700
Data Index: 7657448 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.4604. Min Act: -0.1700
Data Index: 4845792 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.4291. Min Act: -0.1700
Data Index: 3297427 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.4291. Min Act: -0.1700
Data Index: 1325711 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.3979. Min Act: -0.1700
Data Index: 7556210 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.4291. Min Act: -0.1700
Data Index: 2445244 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.3979. Min Act: -0.1700
Data Index: 7698846 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.3979. Min Act: -0.1700
Data Index: 6123565 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.3979. Min Act: -0.1700
Data Index: 4088498 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.4291. Min Act: -0.1700
Data Index: 2256727 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.3979. Min Act: -0.1700
Data Index: 8695166 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.3979. Min Act: -0.1700
Data Index: 2177883 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.3666. Min Act: -0.1700
Data Index: 2581977 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8666. Min Range: -4.8666
Max Act: 4.3979. Min Act: -0.1700
Data Index: 3481749 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19