Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3309. Min Range: -7.3309
Max Act: 7.3309. Min Act: -0.1700
Data Index: 789265 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3309. Min Range: -7.3309
Max Act: 7.0809. Min Act: -0.1700
Data Index: 6811403 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.8309. Min Act: -0.1700
Data Index: 7108213 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.7997. Min Act: -0.1700
Data Index: 1730972 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.7684. Min Act: -0.1700
Data Index: 6088873 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.7997. Min Act: -0.1700
Data Index: 7809498 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.7997. Min Act: -0.1700
Data Index: 3019868 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.7059. Min Act: -0.1700
Data Index: 5970950 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.6434. Min Act: -0.1700
Data Index: 7967544 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.6122. Min Act: -0.1700
Data Index: 7853004 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.6122. Min Act: -0.1700
Data Index: 3236796 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.6122. Min Act: -0.1700
Data Index: 2751868 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.5809. Min Act: -0.1700
Data Index: 1361582 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.5809. Min Act: -0.1700
Data Index: 3851360 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.5809. Min Act: -0.1700
Data Index: 5381569 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.5809. Min Act: -0.1700
Data Index: 7190641 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.5497. Min Act: -0.1700
Data Index: 2541934 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.5497. Min Act: -0.1700
Data Index: 6958365 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.5497. Min Act: -0.1700
Data Index: 2145332 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3309. Min Range: -7.3309
Max Act: 6.5184. Min Act: -0.1700
Data Index: 4372817 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #19