Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 121 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0138. Min Range: -7.0138
Max Act: 7.0138. Min Act: -0.1700
Data Index: 7654506 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.9200. Min Act: -0.1700
Data Index: 7691901 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.8888. Min Act: -0.1700
Data Index: 7198309 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.8575. Min Act: -0.1700
Data Index: 5029266 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.8263. Min Act: -0.1700
Data Index: 4574458 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.7950. Min Act: -0.1700
Data Index: 4799086 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.7638. Min Act: -0.1700
Data Index: 3149519 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.7638. Min Act: -0.1700
Data Index: 7898854 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.7325. Min Act: -0.1700
Data Index: 4002376 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.7325. Min Act: -0.1700
Data Index: 4561664 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.7013. Min Act: -0.1700
Data Index: 6979218 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.7325. Min Act: -0.1700
Data Index: 8222117 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.7013. Min Act: -0.1700
Data Index: 4077133 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.6388. Min Act: -0.1700
Data Index: 5515349 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.6700. Min Act: -0.1700
Data Index: 2826515 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.6388. Min Act: -0.1700
Data Index: 7360250 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.6388. Min Act: -0.1700
Data Index: 6769475 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.6388. Min Act: -0.1700
Data Index: 2103180 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.6388. Min Act: -0.1700
Data Index: 5818748 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0138. Min Range: -7.0138
Max Act: 6.6388. Min Act: -0.1700
Data Index: 489061 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19