Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1212 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.8746. Min Act: -0.1700
Data Index: 8085526 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.6246. Min Act: -0.1700
Data Index: 149542 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.6246. Min Act: -0.1700
Data Index: 5074748 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.5621. Min Act: -0.1700
Data Index: 149543 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.4996. Min Act: -0.1700
Data Index: 3630482 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.4684. Min Act: -0.1700
Data Index: 3437385 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.4371. Min Act: -0.1700
Data Index: 6739964 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.4059. Min Act: -0.1700
Data Index: 8085539 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.4059. Min Act: -0.1700
Data Index: 5744113 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.4059. Min Act: -0.1700
Data Index: 3630477 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.3434. Min Act: -0.1700
Data Index: 5146489 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.3434. Min Act: -0.1700
Data Index: 3288542 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.2184. Min Act: -0.1700
Data Index: 183200 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.2496. Min Act: -0.1700
Data Index: 5744115 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.2496. Min Act: -0.1700
Data Index: 8085533 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.2496. Min Act: -0.1700
Data Index: 8085529 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.1871. Min Act: -0.1700
Data Index: 7527268 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.2496. Min Act: -0.1700
Data Index: 5471295 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.2184. Min Act: -0.1700
Data Index: 8085527 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8746. Min Range: -8.8746
Max Act: 8.2184. Min Act: -0.1700
Data Index: 4337711 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19