Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4348 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.4257. Min Act: -0.1700
Data Index: 7925846 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.4257. Min Act: -0.1700
Data Index: 4849697 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3767. Min Act: -0.1700
Data Index: 2365803 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3604. Min Act: -0.1700
Data Index: 2950547 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3440. Min Act: -0.1700
Data Index: 4977837 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3440. Min Act: -0.1700
Data Index: 338266 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3440. Min Act: -0.1700
Data Index: 7330089 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3112. Min Act: -0.1700
Data Index: 3124265 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3276. Min Act: -0.1700
Data Index: 7827289 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3112. Min Act: -0.1700
Data Index: 2254173 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2947. Min Act: -0.1700
Data Index: 6091993 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.3112. Min Act: -0.1700
Data Index: 5517881 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2617. Min Act: -0.1700
Data Index: 280935 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2947. Min Act: -0.1700
Data Index: 641895 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2782. Min Act: -0.1700
Data Index: 7055301 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2782. Min Act: -0.1700
Data Index: 3848893 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2782. Min Act: -0.1700
Data Index: 5649989 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2782. Min Act: -0.1700
Data Index: 1378518 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2617. Min Act: -0.1700
Data Index: 5085890 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4257. Min Range: -2.4257
Max Act: 2.2617. Min Act: -0.1700
Data Index: 1832892 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #19