Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3249 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.8684. Min Act: -0.1700
Data Index: 3648211 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.8059. Min Act: -0.1700
Data Index: 4697872 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.7434. Min Act: -0.1700
Data Index: 2680940 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.6809. Min Act: -0.1700
Data Index: 7681231 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.6809. Min Act: -0.1700
Data Index: 6813080 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.6184. Min Act: -0.1700
Data Index: 6999164 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.5559. Min Act: -0.1700
Data Index: 4288426 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.5559. Min Act: -0.1700
Data Index: 1983077 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.4934. Min Act: -0.1700
Data Index: 3833261 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.4934. Min Act: -0.1700
Data Index: 7960472 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.4309. Min Act: -0.1700
Data Index: 5428063 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.4309. Min Act: -0.1700
Data Index: 788815 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.3684. Min Act: -0.1700
Data Index: 2733787 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.3684. Min Act: -0.1700
Data Index: 2029131 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.3684. Min Act: -0.1700
Data Index: 3373589 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.3684. Min Act: -0.1700
Data Index: 3122224 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.3684. Min Act: -0.1700
Data Index: 4124101 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.3059. Min Act: -0.1700
Data Index: 3467555 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.3059. Min Act: -0.1700
Data Index: 5702876 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8684. Min Range: -8.8684
Max Act: 8.3059. Min Act: -0.1700
Data Index: 5674711 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19