Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3800 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.8565. Min Act: -0.1700
Data Index: 3936301 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.7315. Min Act: -0.1700
Data Index: 3927387 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.7315. Min Act: -0.1700
Data Index: 6383436 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.6065. Min Act: -0.1700
Data Index: 4887508 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.5440. Min Act: -0.1700
Data Index: 5145696 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.5127. Min Act: -0.1700
Data Index: 5010850 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.5127. Min Act: -0.1700
Data Index: 3547950 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.5127. Min Act: -0.1700
Data Index: 2959372 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4502. Min Act: -0.1700
Data Index: 3389525 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4815. Min Act: -0.1700
Data Index: 6540968 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4190. Min Act: -0.1700
Data Index: 8411145 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4502. Min Act: -0.1700
Data Index: 6435807 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.5127. Min Act: -0.1700
Data Index: 2936892 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4815. Min Act: -0.1700
Data Index: 6575404 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4190. Min Act: -0.1700
Data Index: 6069328 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4190. Min Act: -0.1700
Data Index: 19115 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4190. Min Act: -0.1700
Data Index: 5156796 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4190. Min Act: -0.1700
Data Index: 7373756 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4190. Min Act: -0.1700
Data Index: 6179856 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8565. Min Range: -5.8565
Max Act: 5.4190. Min Act: -0.1700
Data Index: 2689008 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19