Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2428 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2564. Min Range: -8.2564
Max Act: 8.2564. Min Act: -0.1700
Data Index: 3182632 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.9751. Min Act: -0.1700
Data Index: 6789358 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.8814. Min Act: -0.1700
Data Index: 3778800 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.7876. Min Act: -0.1700
Data Index: 6225332 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.6939. Min Act: -0.1700
Data Index: 1154717 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.6626. Min Act: -0.1700
Data Index: 8662879 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.6626. Min Act: -0.1700
Data Index: 2902084 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.6626. Min Act: -0.1700
Data Index: 2902082 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.6314. Min Act: -0.1700
Data Index: 5142697 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.6001. Min Act: -0.1700
Data Index: 8073807 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.5689. Min Act: -0.1700
Data Index: 3699233 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.5376. Min Act: -0.1700
Data Index: 2902067 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.5376. Min Act: -0.1700
Data Index: 2902079 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.5376. Min Act: -0.1700
Data Index: 2902075 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.5064. Min Act: -0.1700
Data Index: 2902068 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.5064. Min Act: -0.1700
Data Index: 3981206 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.4751. Min Act: -0.1700
Data Index: 4370620 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.4439. Min Act: -0.1700
Data Index: 5490184 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.4439. Min Act: -0.1700
Data Index: 7186282 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2564. Min Range: -8.2564
Max Act: 7.4439. Min Act: -0.1700
Data Index: 4841956 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19