Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3977 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.8951. Min Act: -0.1700
Data Index: 1463117 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.8951. Min Act: -0.1700
Data Index: 3881945 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.7701. Min Act: -0.1700
Data Index: 660068 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.4888. Min Act: -0.1700
Data Index: 1740774 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.4576. Min Act: -0.1700
Data Index: 2874144 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.4576. Min Act: -0.1700
Data Index: 5825142 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.4576. Min Act: -0.1700
Data Index: 3145277 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.4263. Min Act: -0.1700
Data Index: 5785294 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.4263. Min Act: -0.1700
Data Index: 7599198 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.3951. Min Act: -0.1700
Data Index: 7748213 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.4263. Min Act: -0.1700
Data Index: 6715505 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.3013. Min Act: -0.1700
Data Index: 8152549 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.3013. Min Act: -0.1700
Data Index: 8550053 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.3013. Min Act: -0.1700
Data Index: 5917237 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.2701. Min Act: -0.1700
Data Index: 5526967 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.2076. Min Act: -0.1700
Data Index: 6461594 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.2388. Min Act: -0.1700
Data Index: 703331 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.2388. Min Act: -0.1700
Data Index: 497358 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.2076. Min Act: -0.1700
Data Index: 1274549 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8951. Min Range: -6.8951
Max Act: 6.2076. Min Act: -0.1700
Data Index: 5413507 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19