Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2773 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0435. Min Range: -10.0435
Max Act: 10.0435. Min Act: -0.1700
Data Index: 2087267 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.8560. Min Act: -0.1700
Data Index: 2883508 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.7310. Min Act: -0.1700
Data Index: 7941504 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.7310. Min Act: -0.1700
Data Index: 3287647 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.6685. Min Act: -0.1700
Data Index: 3486942 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.6685. Min Act: -0.1700
Data Index: 8753618 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.6060. Min Act: -0.1700
Data Index: 4881453 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.5435. Min Act: -0.1700
Data Index: 83787 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.4810. Min Act: -0.1700
Data Index: 5022671 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.4185. Min Act: -0.1700
Data Index: 2504193 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.3560. Min Act: -0.1700
Data Index: 2392179 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.3560. Min Act: -0.1700
Data Index: 5416636 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.3560. Min Act: -0.1700
Data Index: 5438514 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.2935. Min Act: -0.1700
Data Index: 6574346 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.3560. Min Act: -0.1700
Data Index: 5721248 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.3560. Min Act: -0.1700
Data Index: 6195194 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.3560. Min Act: -0.1700
Data Index: 6651284 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.2935. Min Act: -0.1700
Data Index: 3896317 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.2935. Min Act: -0.1700
Data Index: 4565903 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0435. Min Range: -10.0435
Max Act: 9.3560. Min Act: -0.1700
Data Index: 4715671 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19