Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.4138. Min Act: -0.1700
Data Index: 2844236 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.3200. Min Act: -0.1700
Data Index: 3703395 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.3200. Min Act: -0.1700
Data Index: 7273636 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.2575. Min Act: -0.1700
Data Index: 7310030 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1950. Min Act: -0.1700
Data Index: 1836210 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1950. Min Act: -0.1700
Data Index: 5303642 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1950. Min Act: -0.1700
Data Index: 4108191 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.2262. Min Act: -0.1700
Data Index: 1517515 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.2262. Min Act: -0.1700
Data Index: 7217820 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1950. Min Act: -0.1700
Data Index: 1695833 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1637. Min Act: -0.1700
Data Index: 1662961 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1325. Min Act: -0.1700
Data Index: 3350761 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1325. Min Act: -0.1700
Data Index: 8569596 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1012. Min Act: -0.1700
Data Index: 7910708 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1012. Min Act: -0.1700
Data Index: 4954686 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1012. Min Act: -0.1700
Data Index: 4397588 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1012. Min Act: -0.1700
Data Index: 6811202 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1012. Min Act: -0.1700
Data Index: 3991180 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1012. Min Act: -0.1700
Data Index: 6181993 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4138. Min Range: -4.4138
Max Act: 4.1012. Min Act: -0.1700
Data Index: 6060941 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19