Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1520 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.5446. Min Act: -0.1700
Data Index: 4338302 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.4821. Min Act: -0.1700
Data Index: 3595418 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.4196. Min Act: -0.1700
Data Index: 2231915 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.3571. Min Act: -0.1700
Data Index: 4782984 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2946. Min Act: -0.1700
Data Index: 5711237 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2946. Min Act: -0.1700
Data Index: 4051131 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2946. Min Act: -0.1700
Data Index: 1771583 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2946. Min Act: -0.1700
Data Index: 1778306 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2321. Min Act: -0.1700
Data Index: 3180297 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2321. Min Act: -0.1700
Data Index: 593644 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.1696. Min Act: -0.1700
Data Index: 7580090 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2321. Min Act: -0.1700
Data Index: 3188278 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2321. Min Act: -0.1700
Data Index: 4253149 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2321. Min Act: -0.1700
Data Index: 6038084 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.1696. Min Act: -0.1700
Data Index: 4584357 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2321. Min Act: -0.1700
Data Index: 7073871 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.1696. Min Act: -0.1700
Data Index: 7567715 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.1696. Min Act: -0.1700
Data Index: 4194982 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.2321. Min Act: -0.1700
Data Index: 5571015 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5446. Min Range: -8.5446
Max Act: 8.1696. Min Act: -0.1700
Data Index: 2585174 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #19