Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 835 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.3480. Min Act: -0.1700
Data Index: 4419969 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.3480. Min Act: -0.1700
Data Index: 2737777 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.2855. Min Act: -0.1700
Data Index: 997105 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.2543. Min Act: -0.1700
Data Index: 8559621 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.2543. Min Act: -0.1700
Data Index: 6777125 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.2230. Min Act: -0.1700
Data Index: 4760400 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.2230. Min Act: -0.1700
Data Index: 1981346 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.1918. Min Act: -0.1700
Data Index: 8699393 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.1918. Min Act: -0.1700
Data Index: 6290357 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.1918. Min Act: -0.1700
Data Index: 1001481 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.1605. Min Act: -0.1700
Data Index: 1177122 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.1605. Min Act: -0.1700
Data Index: 1568432 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.1605. Min Act: -0.1700
Data Index: 137643 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.1293. Min Act: -0.1700
Data Index: 3753750 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.1293. Min Act: -0.1700
Data Index: 549063 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.0980. Min Act: -0.1700
Data Index: 1306579 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.0980. Min Act: -0.1700
Data Index: 7749268 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.0668. Min Act: -0.1700
Data Index: 7155048 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.0668. Min Act: -0.1700
Data Index: 8300501 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3480. Min Range: -6.3480
Max Act: 6.0668. Min Act: -0.1700
Data Index: 6832971 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19