Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.7905. Min Act: -0.1700
Data Index: 8188724 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.7905. Min Act: -0.1700
Data Index: 7210248 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.7905. Min Act: -0.1700
Data Index: 177151 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.7280. Min Act: -0.1700
Data Index: 4530273 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.7280. Min Act: -0.1700
Data Index: 7828489 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6967. Min Act: -0.1700
Data Index: 7190789 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6967. Min Act: -0.1700
Data Index: 2725415 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6967. Min Act: -0.1700
Data Index: 7015700 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6655. Min Act: -0.1700
Data Index: 2162489 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6655. Min Act: -0.1700
Data Index: 933215 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6655. Min Act: -0.1700
Data Index: 8156566 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6655. Min Act: -0.1700
Data Index: 3808175 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6342. Min Act: -0.1700
Data Index: 4375301 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6655. Min Act: -0.1700
Data Index: 2782694 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6655. Min Act: -0.1700
Data Index: 658983 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6655. Min Act: -0.1700
Data Index: 2832356 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6342. Min Act: -0.1700
Data Index: 7639439 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6342. Min Act: -0.1700
Data Index: 2725405 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.6342. Min Act: -0.1700
Data Index: 5494188 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7905. Min Range: -4.7905
Max Act: 4.5717. Min Act: -0.1700
Data Index: 390864 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19