Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.4523. Min Act: -0.1700
Data Index: 6092567 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.3585. Min Act: -0.1700
Data Index: 5306429 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.3585. Min Act: -0.1700
Data Index: 8298161 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.2960. Min Act: -0.1700
Data Index: 1288568 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.2960. Min Act: -0.1700
Data Index: 8620101 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.2335. Min Act: -0.1700
Data Index: 2367329 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.2335. Min Act: -0.1700
Data Index: 4230948 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.2023. Min Act: -0.1700
Data Index: 254375 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.1398. Min Act: -0.1700
Data Index: 2865544 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.2335. Min Act: -0.1700
Data Index: 5611959 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.1710. Min Act: -0.1700
Data Index: 4594379 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.1085. Min Act: -0.1700
Data Index: 914492 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.1398. Min Act: -0.1700
Data Index: 6535890 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.2023. Min Act: -0.1700
Data Index: 2711841 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.1710. Min Act: -0.1700
Data Index: 4410436 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.1085. Min Act: -0.1700
Data Index: 5056549 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.1710. Min Act: -0.1700
Data Index: 7496063 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.1085. Min Act: -0.1700
Data Index: 2273048 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.1085. Min Act: -0.1700
Data Index: 6213632 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4523. Min Range: -6.4523
Max Act: 6.1398. Min Act: -0.1700
Data Index: 109192 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19