Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 670 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.3090. Min Act: -0.1700
Data Index: 3341178 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.2152. Min Act: -0.1700
Data Index: 7392203 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.1214. Min Act: -0.1700
Data Index: 1861771 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0902. Min Act: -0.1700
Data Index: 6141667 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0902. Min Act: -0.1700
Data Index: 8402798 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.1214. Min Act: -0.1700
Data Index: 1697558 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3090. Min Range: -4.3090
Max Act: 3.9964. Min Act: -0.1700
Data Index: 4670 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.1214. Min Act: -0.1700
Data Index: 1861766 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.1214. Min Act: -0.1700
Data Index: 812559 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3090. Min Range: -4.3090
Max Act: 3.9964. Min Act: -0.1700
Data Index: 307712 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0589. Min Act: -0.1700
Data Index: 3549463 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0902. Min Act: -0.1700
Data Index: 6713547 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0277. Min Act: -0.1700
Data Index: 868604 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0902. Min Act: -0.1700
Data Index: 6334230 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0589. Min Act: -0.1700
Data Index: 5642588 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3090. Min Range: -4.3090
Max Act: 3.8714. Min Act: -0.1700
Data Index: 3390764 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0902. Min Act: -0.1700
Data Index: 5003391 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0277. Min Act: -0.1700
Data Index: 202094 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0277. Min Act: -0.1700
Data Index: 3302066 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3090. Min Range: -4.3090
Max Act: 4.0277. Min Act: -0.1700
Data Index: 2915335 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19